Compare commits
1 Commits
0055ea2df7
...
dynamic_pl
| Author | SHA1 | Date | |
|---|---|---|---|
|
d2dd5d3eb1 |
56
.github/workflows/conda-pack-windows.yml
vendored
56
.github/workflows/conda-pack-windows.yml
vendored
@@ -1,56 +0,0 @@
|
||||
name: Create Conda Environment Package
|
||||
|
||||
on:
|
||||
workflow_dispatch:
|
||||
|
||||
jobs:
|
||||
build:
|
||||
runs-on: windows-latest
|
||||
|
||||
steps:
|
||||
- name: Checkout repository
|
||||
uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Miniconda
|
||||
uses: conda-incubator/setup-miniconda@v3
|
||||
with:
|
||||
auto-activate-base: true
|
||||
activate-environment: ""
|
||||
|
||||
- name: Create new Conda environment
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
conda create -n gpt python=3.11 -y
|
||||
conda activate gpt
|
||||
|
||||
- name: Install requirements
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
conda activate gpt
|
||||
pip install -r requirements.txt
|
||||
|
||||
- name: Install conda-pack
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
conda activate gpt
|
||||
conda install conda-pack -y
|
||||
|
||||
- name: Pack conda environment
|
||||
shell: bash -l {0}
|
||||
run: |
|
||||
conda activate gpt
|
||||
conda pack -n gpt -o gpt.tar.gz
|
||||
|
||||
- name: Create workspace zip
|
||||
shell: pwsh
|
||||
run: |
|
||||
mkdir workspace
|
||||
Get-ChildItem -Exclude "workspace" | Copy-Item -Destination workspace -Recurse
|
||||
Remove-Item -Path workspace/.git* -Recurse -Force -ErrorAction SilentlyContinue
|
||||
Copy-Item gpt.tar.gz workspace/ -Force
|
||||
|
||||
- name: Upload packed files
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: gpt-academic-package
|
||||
path: workspace
|
||||
7
.github/workflows/stale.yml
vendored
7
.github/workflows/stale.yml
vendored
@@ -7,7 +7,7 @@
|
||||
name: 'Close stale issues and PRs'
|
||||
on:
|
||||
schedule:
|
||||
- cron: '*/30 * * * *'
|
||||
- cron: '*/5 * * * *'
|
||||
|
||||
jobs:
|
||||
stale:
|
||||
@@ -19,6 +19,7 @@ jobs:
|
||||
steps:
|
||||
- uses: actions/stale@v8
|
||||
with:
|
||||
stale-issue-message: 'This issue is stale because it has been open 100 days with no activity. Remove stale label or comment or this will be closed in 7 days.'
|
||||
stale-issue-message: 'This issue is stale because it has been open 100 days with no activity. Remove stale label or comment or this will be closed in 1 days.'
|
||||
days-before-stale: 100
|
||||
days-before-close: 7
|
||||
days-before-close: 1
|
||||
debug-only: true
|
||||
|
||||
@@ -15,7 +15,6 @@ RUN echo '[global]' > /etc/pip.conf && \
|
||||
# 语音输出功能（以下两行，第一行更换阿里源，第二行安装ffmpeg，都可以删除）
|
||||
RUN UBUNTU_VERSION=$(awk -F= '/^VERSION_CODENAME=/{print $2}' /etc/os-release); echo "deb https://mirrors.aliyun.com/debian/ $UBUNTU_VERSION main non-free contrib" > /etc/apt/sources.list; apt-get update
|
||||
RUN apt-get install ffmpeg -y
|
||||
RUN apt-get clean
|
||||
|
||||
|
||||
# 进入工作路径（必要）
|
||||
@@ -34,7 +33,6 @@ RUN pip3 install -r requirements.txt
|
||||
|
||||
# 非必要步骤，用于预热模块（可以删除）
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
RUN python3 -m pip cache purge
|
||||
|
||||
|
||||
# 启动（必要）
|
||||
|
||||
52
README.md
52
README.md
@@ -1,14 +1,9 @@
|
||||
> [!IMPORTANT]
|
||||
> `master主分支`最新动态(2025.3.2): 修复大量代码typo / 联网组件支持Jina的api / 增加deepseek-r1支持
|
||||
> `frontier开发分支`最新动态(2024.12.9): 更新对话时间线功能，优化xelatex论文翻译
|
||||
> `wiki文档`最新动态(2024.12.5): 更新ollama接入指南
|
||||
>
|
||||
> 2025.2.2: 三分钟快速接入最强qwen2.5-max[视频](https://www.bilibili.com/video/BV1LeFuerEG4)
|
||||
> 2025.2.1: 支持自定义字体
|
||||
> 2024.10.10: 突发停电，紧急恢复了提供[whl包](https://drive.google.com/drive/folders/14kR-3V-lIbvGxri4AHc8TpiA1fqsw7SK?usp=sharing)的文件服务器
|
||||
> 2024.10.10: 突发停电，紧急恢复了提供[whl包](https://drive.google.com/file/d/19U_hsLoMrjOlQSzYS3pzWX9fTzyusArP/view?usp=sharing)的文件服务器
|
||||
> 2024.10.8: 版本3.90加入对llama-index的初步支持，版本3.80加入插件二级菜单功能（详见wiki）
|
||||
> 2024.5.1: 加入Doc2x翻译PDF论文的功能，[查看详情](https://github.com/binary-husky/gpt_academic/wiki/Doc2x)
|
||||
> 2024.3.11: 全力支持Qwen、GLM、DeepseekCoder等中文大语言模型！ SoVits语音克隆模块，[查看详情](https://www.bilibili.com/video/BV1Rp421S7tF/)
|
||||
> 2024.1.17: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。
|
||||
> 2024.1.17: 安装依赖时，请选择`requirements.txt`中**指定的版本**。 安装命令：`pip install -r requirements.txt`。本项目完全开源免费，您可通过订阅[在线服务](https://github.com/binary-husky/gpt_academic/wiki/online)的方式鼓励本项目的发展。
|
||||
|
||||
<br>
|
||||
|
||||
@@ -129,20 +124,20 @@ Latex论文一键校对 | [插件] 仿Grammarly对Latex文章进行语法、拼
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
A{"安装方法"} --> W1("I 🔑直接运行 (Windows, Linux or MacOS)")
|
||||
W1 --> W11["1 Python pip包管理依赖"]
|
||||
W1 --> W12["2 Anaconda包管理依赖（推荐⭐）"]
|
||||
A{"安装方法"} --> W1("I. 🔑直接运行 (Windows, Linux or MacOS)")
|
||||
W1 --> W11["1. Python pip包管理依赖"]
|
||||
W1 --> W12["2. Anaconda包管理依赖（推荐⭐）"]
|
||||
|
||||
A --> W2["II 🐳使用Docker (Windows, Linux or MacOS)"]
|
||||
A --> W2["II. 🐳使用Docker (Windows, Linux or MacOS)"]
|
||||
|
||||
W2 --> k1["1 部署项目全部能力的大镜像（推荐⭐）"]
|
||||
W2 --> k2["2 仅在线模型（GPT, GLM4等）镜像"]
|
||||
W2 --> k3["3 在线模型 + Latex的大镜像"]
|
||||
W2 --> k1["1. 部署项目全部能力的大镜像（推荐⭐）"]
|
||||
W2 --> k2["2. 仅在线模型（GPT, GLM4等）镜像"]
|
||||
W2 --> k3["3. 在线模型 + Latex的大镜像"]
|
||||
|
||||
A --> W4["IV 🚀其他部署方法"]
|
||||
W4 --> C1["1 Windows/MacOS 一键安装运行脚本（推荐⭐）"]
|
||||
W4 --> C2["2 Huggingface, Sealos远程部署"]
|
||||
W4 --> C4["3 其他 ..."]
|
||||
A --> W4["IV. 🚀其他部署方法"]
|
||||
W4 --> C1["1. Windows/MacOS 一键安装运行脚本（推荐⭐）"]
|
||||
W4 --> C2["2. Huggingface, Sealos远程部署"]
|
||||
W4 --> C4["3. ... 其他 ..."]
|
||||
```
|
||||
|
||||
### 安装方法I：直接运行 (Windows, Linux or MacOS)
|
||||
@@ -175,32 +170,26 @@ flowchart TD
|
||||
```
|
||||
|
||||
|
||||
<details><summary>如果需要支持清华ChatGLM系列/复旦MOSS/RWKV作为后端，请点击展开此处</summary>
|
||||
<details><summary>如果需要支持清华ChatGLM2/复旦MOSS/RWKV作为后端，请点击展开此处</summary>
|
||||
<p>
|
||||
|
||||
【可选步骤】如果需要支持清华ChatGLM系列/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
|
||||
【可选步骤】如果需要支持清华ChatGLM3/复旦MOSS作为后端，需要额外安装更多依赖（前提条件：熟悉Python + 用过Pytorch + 电脑配置够强）：
|
||||
|
||||
```sh
|
||||
# 【可选步骤I】支持清华ChatGLM3。清华ChatGLM备注：如果遇到"Call ChatGLM fail 不能正常加载ChatGLM的参数" 错误，参考如下： 1：以上默认安装的为torch+cpu版，使用cuda需要卸载torch重新安装torch+cuda； 2：如因本机配置不够无法加载模型，可以修改request_llm/bridge_chatglm.py中的模型精度, 将 AutoTokenizer.from_pretrained("THUDM/chatglm-6b", trust_remote_code=True) 都修改为 AutoTokenizer.from_pretrained("THUDM/chatglm-6b-int4", trust_remote_code=True)
|
||||
python -m pip install -r request_llms/requirements_chatglm.txt
|
||||
|
||||
# 【可选步骤II】支持清华ChatGLM4 注意：此模型至少需要24G显存
|
||||
python -m pip install -r request_llms/requirements_chatglm4.txt
|
||||
# 可使用modelscope下载ChatGLM4模型
|
||||
# pip install modelscope
|
||||
# modelscope download --model ZhipuAI/glm-4-9b-chat --local_dir ./THUDM/glm-4-9b-chat
|
||||
|
||||
# 【可选步骤III】支持复旦MOSS
|
||||
# 【可选步骤II】支持复旦MOSS
|
||||
python -m pip install -r request_llms/requirements_moss.txt
|
||||
git clone --depth=1 https://github.com/OpenLMLab/MOSS.git request_llms/moss # 注意执行此行代码时，必须处于项目根路径
|
||||
|
||||
# 【可选步骤IV】支持RWKV Runner
|
||||
# 【可选步骤III】支持RWKV Runner
|
||||
参考wiki：https://github.com/binary-husky/gpt_academic/wiki/%E9%80%82%E9%85%8DRWKV-Runner
|
||||
|
||||
# 【可选步骤V】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型，目前支持的全部模型如下(jittorllms系列目前仅支持docker方案)：
|
||||
# 【可选步骤IV】确保config.py配置文件的AVAIL_LLM_MODELS包含了期望的模型，目前支持的全部模型如下(jittorllms系列目前仅支持docker方案)：
|
||||
AVAIL_LLM_MODELS = ["gpt-3.5-turbo", "api2d-gpt-3.5-turbo", "gpt-4", "api2d-gpt-4", "chatglm", "moss"] # + ["jittorllms_rwkv", "jittorllms_pangualpha", "jittorllms_llama"]
|
||||
|
||||
# 【可选步骤VI】支持本地模型INT8,INT4量化（这里所指的模型本身不是量化版本，目前deepseek-coder支持，后面测试后会加入更多模型量化选择）
|
||||
# 【可选步骤V】支持本地模型INT8,INT4量化（这里所指的模型本身不是量化版本，目前deepseek-coder支持，后面测试后会加入更多模型量化选择）
|
||||
pip install bitsandbyte
|
||||
# windows用户安装bitsandbytes需要使用下面bitsandbytes-windows-webui
|
||||
python -m pip install bitsandbytes --prefer-binary --extra-index-url=https://jllllll.github.io/bitsandbytes-windows-webui
|
||||
@@ -428,6 +417,7 @@ timeline LR
|
||||
1. `master` 分支: 主分支，稳定版
|
||||
2. `frontier` 分支: 开发分支，测试版
|
||||
3. 如何[接入其他大模型](request_llms/README.md)
|
||||
4. 访问GPT-Academic的[在线服务并支持我们](https://github.com/binary-husky/gpt_academic/wiki/online)
|
||||
|
||||
### V：参考与学习
|
||||
|
||||
|
||||
75
config.py
75
config.py
@@ -7,16 +7,11 @@
|
||||
Configuration reading priority: environment variable > config_private.py > config.py
|
||||
"""
|
||||
|
||||
# [step 1-1]>> ( 接入GPT等模型 ) API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
|
||||
API_KEY = "在此处填写APIKEY" # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
|
||||
# [step 1]>> API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
|
||||
API_KEY = "此处填API密钥" # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey3,azure-apikey4"
|
||||
|
||||
# [step 1-2]>> ( 接入通义 qwen-max ) 接入通义千问在线大模型，api-key获取地址 https://dashscope.console.aliyun.com/
|
||||
DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
|
||||
|
||||
# [step 1-3]>> ( 接入 deepseek-reasoner, 即 deepseek-r1 ) 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
|
||||
DEEPSEEK_API_KEY = ""
|
||||
|
||||
# [step 2]>> 改为True应用代理。如果使用本地或无地域限制的大模型时，此处不修改；如果直接在海外服务器部署，此处不修改
|
||||
# [step 2]>> 改为True应用代理，如果直接在海外服务器部署，此处不修改；如果使用本地或无地域限制的大模型时，此处也不需要修改
|
||||
USE_PROXY = False
|
||||
if USE_PROXY:
|
||||
"""
|
||||
@@ -37,13 +32,11 @@ else:
|
||||
|
||||
# [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
|
||||
LLM_MODEL = "gpt-3.5-turbo-16k" # 可选 ↓↓↓
|
||||
AVAIL_LLM_MODELS = ["qwen-max", "o1-mini", "o1-mini-2024-09-12", "o1", "o1-2024-12-17", "o1-preview", "o1-preview-2024-09-12",
|
||||
"gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
|
||||
AVAIL_LLM_MODELS = ["gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
|
||||
"gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
|
||||
"gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
|
||||
"gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
|
||||
"gemini-1.5-pro", "chatglm3", "chatglm4",
|
||||
"deepseek-chat", "deepseek-coder", "deepseek-reasoner"
|
||||
"gemini-1.5-pro", "chatglm3"
|
||||
]
|
||||
|
||||
EMBEDDING_MODEL = "text-embedding-3-small"
|
||||
@@ -54,7 +47,7 @@ EMBEDDING_MODEL = "text-embedding-3-small"
|
||||
# "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
|
||||
# "qianfan", "deepseekcoder",
|
||||
# "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
|
||||
# "qwen-turbo", "qwen-plus", "qwen-local",
|
||||
# "qwen-turbo", "qwen-plus", "qwen-max", "qwen-local",
|
||||
# "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
|
||||
# "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125", "gpt-4o-2024-05-13"
|
||||
# "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
|
||||
@@ -62,7 +55,6 @@ EMBEDDING_MODEL = "text-embedding-3-small"
|
||||
# "deepseek-chat" ,"deepseek-coder",
|
||||
# "gemini-1.5-flash",
|
||||
# "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
|
||||
# "grok-beta",
|
||||
# ]
|
||||
# --- --- --- ---
|
||||
# 此外，您还可以在接入one-api/vllm/ollama/Openroute时，
|
||||
@@ -81,7 +73,7 @@ API_URL_REDIRECT = {}
|
||||
|
||||
# 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
|
||||
# 一言以蔽之：免费（5刀）用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
|
||||
DEFAULT_WORKER_NUM = 8
|
||||
DEFAULT_WORKER_NUM = 3
|
||||
|
||||
|
||||
# 色彩主题, 可选 ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast"]
|
||||
@@ -89,31 +81,6 @@ DEFAULT_WORKER_NUM = 8
|
||||
THEME = "Default"
|
||||
AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
|
||||
|
||||
FONT = "Theme-Default-Font"
|
||||
AVAIL_FONTS = [
|
||||
"默认值(Theme-Default-Font)",
|
||||
"宋体(SimSun)",
|
||||
"黑体(SimHei)",
|
||||
"楷体(KaiTi)",
|
||||
"仿宋(FangSong)",
|
||||
"华文细黑(STHeiti Light)",
|
||||
"华文楷体(STKaiti)",
|
||||
"华文仿宋(STFangsong)",
|
||||
"华文宋体(STSong)",
|
||||
"华文中宋(STZhongsong)",
|
||||
"华文新魏(STXinwei)",
|
||||
"华文隶书(STLiti)",
|
||||
# 备注：以下字体需要网络支持，您可以自定义任意您喜欢的字体，如下所示，需要满足的格式为 "字体昵称(字体英文真名@字体css下载链接)"
|
||||
"思源宋体(Source Han Serif CN VF@https://chinese-fonts-cdn.deno.dev/packages/syst/dist/SourceHanSerifCN/result.css)",
|
||||
"月星楷(Moon Stars Kai HW@https://chinese-fonts-cdn.deno.dev/packages/moon-stars-kai/dist/MoonStarsKaiHW-Regular/result.css)",
|
||||
"珠圆体(MaokenZhuyuanTi@https://chinese-fonts-cdn.deno.dev/packages/mkzyt/dist/猫啃珠圆体/result.css)",
|
||||
"平方萌萌哒(PING FANG MENG MNEG DA@https://chinese-fonts-cdn.deno.dev/packages/pfmmd/dist/平方萌萌哒/result.css)",
|
||||
"Helvetica",
|
||||
"ui-sans-serif",
|
||||
"sans-serif",
|
||||
"system-ui"
|
||||
]
|
||||
|
||||
|
||||
# 默认的系统提示词（system prompt）
|
||||
INIT_SYS_PROMPT = "Serve me as a writing and programming assistant."
|
||||
@@ -165,15 +132,16 @@ MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
|
||||
QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
|
||||
|
||||
|
||||
# 接入通义千问在线大模型 https://dashscope.console.aliyun.com/
|
||||
DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
|
||||
|
||||
|
||||
# 百度千帆（LLM_MODEL="qianfan"）
|
||||
BAIDU_CLOUD_API_KEY = ''
|
||||
BAIDU_CLOUD_SECRET_KEY = ''
|
||||
BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot' # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat", "ERNIE-Speed-128K", "ERNIE-Speed-8K", "ERNIE-Lite-8K"
|
||||
|
||||
|
||||
# 如果使用ChatGLM3或ChatGLM4本地模型，请把 LLM_MODEL="chatglm3" 或LLM_MODEL="chatglm4"，并在此处指定模型路径
|
||||
CHATGLM_LOCAL_MODEL_PATH = "THUDM/glm-4-9b-chat" # 例如"/home/hmp/ChatGLM3-6B/"
|
||||
|
||||
# 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
|
||||
CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
|
||||
|
||||
@@ -267,11 +235,13 @@ MOONSHOT_API_KEY = ""
|
||||
YIMODEL_API_KEY = ""
|
||||
|
||||
|
||||
# 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
|
||||
DEEPSEEK_API_KEY = ""
|
||||
|
||||
|
||||
# 紫东太初大模型 https://ai-maas.wair.ac.cn
|
||||
TAICHU_API_KEY = ""
|
||||
|
||||
# Grok API KEY
|
||||
GROK_API_KEY = ""
|
||||
|
||||
# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
|
||||
MATHPIX_APPID = ""
|
||||
@@ -303,8 +273,8 @@ GROBID_URLS = [
|
||||
]
|
||||
|
||||
|
||||
# Searxng互联网检索服务（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
|
||||
SEARXNG_URLS = [ f"https://kaletianlre-beardvs{i}dd.hf.space/" for i in range(1,5) ]
|
||||
# Searxng互联网检索服务
|
||||
SEARXNG_URL = "https://cloud-1.agent-matrix.com/"
|
||||
|
||||
|
||||
# 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
|
||||
@@ -328,7 +298,7 @@ ARXIV_CACHE_DIR = "gpt_log/arxiv_cache"
|
||||
|
||||
|
||||
# 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
|
||||
WHEN_TO_USE_PROXY = ["Connect_OpenAI", "Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
|
||||
WHEN_TO_USE_PROXY = ["Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
|
||||
"Warmup_Modules", "Nougat_Download", "AutoGen", "Connect_OpenAI_Embedding"]
|
||||
|
||||
|
||||
@@ -340,12 +310,6 @@ PLUGIN_HOT_RELOAD = False
|
||||
NUM_CUSTOM_BASIC_BTN = 4
|
||||
|
||||
|
||||
# 媒体智能体的服务地址（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
|
||||
DAAS_SERVER_URLS = [ f"https://niuziniu-biligpt{i}.hf.space/stream" for i in range(1,5) ]
|
||||
|
||||
|
||||
# 在互联网搜索组件中，负责将搜索结果整理成干净的Markdown
|
||||
JINA_API_KEY = ""
|
||||
|
||||
"""
|
||||
--------------- 配置关联关系说明 ---------------
|
||||
@@ -405,7 +369,6 @@ JINA_API_KEY = ""
|
||||
|
||||
本地大模型示意图
|
||||
│
|
||||
├── "chatglm4"
|
||||
├── "chatglm3"
|
||||
├── "chatglm"
|
||||
├── "chatglm_onnx"
|
||||
@@ -436,7 +399,7 @@ JINA_API_KEY = ""
|
||||
插件在线服务配置依赖关系示意图
|
||||
│
|
||||
├── 互联网检索
|
||||
│ └── SEARXNG_URLS
|
||||
│ └── SEARXNG_URL
|
||||
│
|
||||
├── 语音功能
|
||||
│ ├── ENABLE_AUDIO
|
||||
|
||||
@@ -1,444 +0,0 @@
|
||||
"""
|
||||
以下所有配置也都支持利用环境变量覆写，环境变量配置格式见docker-compose.yml。
|
||||
读取优先级：环境变量 > config_private.py > config.py
|
||||
--- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- --- ---
|
||||
All the following configurations also support using environment variables to override,
|
||||
and the environment variable configuration format can be seen in docker-compose.yml.
|
||||
Configuration reading priority: environment variable > config_private.py > config.py
|
||||
"""
|
||||
|
||||
# [step 1-1]>> ( 接入GPT等模型 ) API_KEY = "sk-123456789xxxxxxxxxxxxxxxxxxxxxxxxxxxxxx123456789"。极少数情况下，还需要填写组织（格式如org-123456789abcdefghijklmno的），请向下翻，找 API_ORG 设置项
|
||||
API_KEY = "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" # 可同时填写多个API-KEY，用英文逗号分割，例如API_KEY = "sk-openaikey1,sk-openaikey2,fkxxxx-api2dkey1,fkxxxx-api2dkey2"
|
||||
|
||||
# [step 1-2]>> ( 接入通义 qwen-max ) 接入通义千问在线大模型，api-key获取地址 https://dashscope.console.aliyun.com/
|
||||
DASHSCOPE_API_KEY = "" # 阿里灵积云API_KEY
|
||||
|
||||
# [step 1-3]>> ( 接入 deepseek-reasoner, 即 deepseek-r1 ) 深度求索(DeepSeek) API KEY，默认请求地址为"https://api.deepseek.com/v1/chat/completions"
|
||||
DEEPSEEK_API_KEY = "sk-d99b8cc6b7414cc88a5d950a3ff7585e"
|
||||
|
||||
# [step 2]>> 改为True应用代理。如果使用本地或无地域限制的大模型时，此处不修改；如果直接在海外服务器部署，此处不修改
|
||||
USE_PROXY = True
|
||||
if USE_PROXY:
|
||||
proxies = {
|
||||
"http":"socks5h://192.168.8.9:1070", # 再例如 "http": "http://127.0.0.1:7890",
|
||||
"https":"socks5h://192.168.8.9:1070", # 再例如 "https": "http://127.0.0.1:7890",
|
||||
}
|
||||
else:
|
||||
proxies = None
|
||||
DEFAULT_WORKER_NUM = 256
|
||||
|
||||
# [step 3]>> 模型选择是 (注意: LLM_MODEL是默认选中的模型, 它*必须*被包含在AVAIL_LLM_MODELS列表中 )
|
||||
LLM_MODEL = "gpt-4-32k" # 可选 ↓↓↓
|
||||
AVAIL_LLM_MODELS = ["deepseek-chat", "deepseek-coder", "deepseek-reasoner",
|
||||
"gpt-4-1106-preview", "gpt-4-turbo-preview", "gpt-4-vision-preview",
|
||||
"gpt-4o", "gpt-4o-mini", "gpt-4-turbo", "gpt-4-turbo-2024-04-09",
|
||||
"gpt-3.5-turbo-1106", "gpt-3.5-turbo-16k", "gpt-3.5-turbo", "azure-gpt-3.5",
|
||||
"gpt-4", "gpt-4-32k", "azure-gpt-4", "glm-4", "glm-4v", "glm-3-turbo",
|
||||
"gemini-1.5-pro", "chatglm3", "chatglm4",
|
||||
]
|
||||
|
||||
EMBEDDING_MODEL = "text-embedding-3-small"
|
||||
|
||||
# --- --- --- ---
|
||||
# P.S. 其他可用的模型还包括
|
||||
# AVAIL_LLM_MODELS = [
|
||||
# "glm-4-0520", "glm-4-air", "glm-4-airx", "glm-4-flash",
|
||||
# "qianfan", "deepseekcoder",
|
||||
# "spark", "sparkv2", "sparkv3", "sparkv3.5", "sparkv4",
|
||||
# "qwen-turbo", "qwen-plus", "qwen-local",
|
||||
# "moonshot-v1-128k", "moonshot-v1-32k", "moonshot-v1-8k",
|
||||
# "gpt-3.5-turbo-0613", "gpt-3.5-turbo-16k-0613", "gpt-3.5-turbo-0125", "gpt-4o-2024-05-13"
|
||||
# "claude-3-haiku-20240307","claude-3-sonnet-20240229","claude-3-opus-20240229", "claude-2.1", "claude-instant-1.2",
|
||||
# "moss", "llama2", "chatglm_onnx", "internlm", "jittorllms_pangualpha", "jittorllms_llama",
|
||||
# "deepseek-chat" ,"deepseek-coder",
|
||||
# "gemini-1.5-flash",
|
||||
# "yi-34b-chat-0205","yi-34b-chat-200k","yi-large","yi-medium","yi-spark","yi-large-turbo","yi-large-preview",
|
||||
# "grok-beta",
|
||||
# ]
|
||||
# --- --- --- ---
|
||||
# 此外，您还可以在接入one-api/vllm/ollama/Openroute时，
|
||||
# 使用"one-api-*","vllm-*","ollama-*","openrouter-*"前缀直接使用非标准方式接入的模型，例如
|
||||
# AVAIL_LLM_MODELS = ["one-api-claude-3-sonnet-20240229(max_token=100000)", "ollama-phi3(max_token=4096)","openrouter-openai/gpt-4o-mini","openrouter-openai/chatgpt-4o-latest"]
|
||||
# --- --- --- ---
|
||||
|
||||
|
||||
# --------------- 以下配置可以优化体验 ---------------
|
||||
|
||||
# 重新URL重新定向，实现更换API_URL的作用（高危设置! 常规情况下不要修改! 通过修改此设置，您将把您的API-KEY和对话隐私完全暴露给您设定的中间人！）
|
||||
# 格式: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "在这里填写重定向的api.openai.com的URL"}
|
||||
# 举例: API_URL_REDIRECT = {"https://api.openai.com/v1/chat/completions": "https://reverse-proxy-url/v1/chat/completions", "http://localhost:11434/api/chat": "在这里填写您ollama的URL"}
|
||||
API_URL_REDIRECT = {}
|
||||
|
||||
|
||||
# 多线程函数插件中，默认允许多少路线程同时访问OpenAI。Free trial users的限制是每分钟3次，Pay-as-you-go users的限制是每分钟3500次
|
||||
# 一言以蔽之：免费（5刀）用户填3，OpenAI绑了信用卡的用户可以填 16 或者更高。提高限制请查询：https://platform.openai.com/docs/guides/rate-limits/overview
|
||||
DEFAULT_WORKER_NUM = 64
|
||||
|
||||
|
||||
# 色彩主题, 可选 ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast"]
|
||||
# 更多主题, 请查阅Gradio主题商店: https://huggingface.co/spaces/gradio/theme-gallery 可选 ["Gstaff/Xkcd", "NoCrypt/Miku", ...]
|
||||
THEME = "Default"
|
||||
AVAIL_THEMES = ["Default", "Chuanhu-Small-and-Beautiful", "High-Contrast", "Gstaff/Xkcd", "NoCrypt/Miku"]
|
||||
|
||||
FONT = "Theme-Default-Font"
|
||||
AVAIL_FONTS = [
|
||||
"默认值(Theme-Default-Font)",
|
||||
"宋体(SimSun)",
|
||||
"黑体(SimHei)",
|
||||
"楷体(KaiTi)",
|
||||
"仿宋(FangSong)",
|
||||
"华文细黑(STHeiti Light)",
|
||||
"华文楷体(STKaiti)",
|
||||
"华文仿宋(STFangsong)",
|
||||
"华文宋体(STSong)",
|
||||
"华文中宋(STZhongsong)",
|
||||
"华文新魏(STXinwei)",
|
||||
"华文隶书(STLiti)",
|
||||
"思源宋体(Source Han Serif CN VF@https://chinese-fonts-cdn.deno.dev/packages/syst/dist/SourceHanSerifCN/result.css)",
|
||||
"月星楷(Moon Stars Kai HW@https://chinese-fonts-cdn.deno.dev/packages/moon-stars-kai/dist/MoonStarsKaiHW-Regular/result.css)",
|
||||
"珠圆体(MaokenZhuyuanTi@https://chinese-fonts-cdn.deno.dev/packages/mkzyt/dist/猫啃珠圆体/result.css)",
|
||||
"平方萌萌哒(PING FANG MENG MNEG DA@https://chinese-fonts-cdn.deno.dev/packages/pfmmd/dist/平方萌萌哒/result.css)",
|
||||
"Helvetica",
|
||||
"ui-sans-serif",
|
||||
"sans-serif",
|
||||
"system-ui"
|
||||
]
|
||||
|
||||
|
||||
# 默认的系统提示词（system prompt）
|
||||
INIT_SYS_PROMPT = "Serve me as a writing and programming assistant."
|
||||
|
||||
|
||||
# 对话窗的高度 （仅在LAYOUT="TOP-DOWN"时生效）
|
||||
CHATBOT_HEIGHT = 1115
|
||||
|
||||
|
||||
# 代码高亮
|
||||
CODE_HIGHLIGHT = True
|
||||
|
||||
|
||||
# 窗口布局
|
||||
LAYOUT = "LEFT-RIGHT" # "LEFT-RIGHT"（左右布局） # "TOP-DOWN"（上下布局）
|
||||
|
||||
|
||||
# 暗色模式 / 亮色模式
|
||||
DARK_MODE = True
|
||||
|
||||
|
||||
# 发送请求到OpenAI后，等待多久判定为超时
|
||||
TIMEOUT_SECONDS = 60
|
||||
|
||||
|
||||
# 网页的端口, -1代表随机端口
|
||||
WEB_PORT = 19998
|
||||
|
||||
# 是否自动打开浏览器页面
|
||||
AUTO_OPEN_BROWSER = True
|
||||
|
||||
|
||||
# 如果OpenAI不响应（网络卡顿、代理失败、KEY失效），重试的次数限制
|
||||
MAX_RETRY = 5
|
||||
|
||||
|
||||
# 插件分类默认选项
|
||||
DEFAULT_FN_GROUPS = ['对话', '编程', '学术', '智能体']
|
||||
|
||||
|
||||
# 定义界面上“询问多个GPT模型”插件应该使用哪些模型，请从AVAIL_LLM_MODELS中选择，并在不同模型之间用`&`间隔，例如"gpt-3.5-turbo&chatglm3&azure-gpt-4"
|
||||
MULTI_QUERY_LLM_MODELS = "gpt-3.5-turbo&chatglm3"
|
||||
|
||||
|
||||
# 选择本地模型变体（只有当AVAIL_LLM_MODELS包含了对应本地模型时，才会起作用）
|
||||
# 如果你选择Qwen系列的模型，那么请在下面的QWEN_MODEL_SELECTION中指定具体的模型
|
||||
# 也可以是具体的模型路径
|
||||
QWEN_LOCAL_MODEL_SELECTION = "Qwen/Qwen-1_8B-Chat-Int8"
|
||||
|
||||
|
||||
# 百度千帆（LLM_MODEL="qianfan"）
|
||||
BAIDU_CLOUD_API_KEY = ''
|
||||
BAIDU_CLOUD_SECRET_KEY = ''
|
||||
BAIDU_CLOUD_QIANFAN_MODEL = 'ERNIE-Bot' # 可选 "ERNIE-Bot-4"(文心大模型4.0), "ERNIE-Bot"(文心一言), "ERNIE-Bot-turbo", "BLOOMZ-7B", "Llama-2-70B-Chat", "Llama-2-13B-Chat", "Llama-2-7B-Chat", "ERNIE-Speed-128K", "ERNIE-Speed-8K", "ERNIE-Lite-8K"
|
||||
|
||||
|
||||
# 如果使用ChatGLM3或ChatGLM4本地模型，请把 LLM_MODEL="chatglm3" 或LLM_MODEL="chatglm4"，并在此处指定模型路径
|
||||
CHATGLM_LOCAL_MODEL_PATH = "THUDM/glm-4-9b-chat" # 例如"/home/hmp/ChatGLM3-6B/"
|
||||
|
||||
# 如果使用ChatGLM2微调模型，请把 LLM_MODEL="chatglmft"，并在此处指定模型路径
|
||||
CHATGLM_PTUNING_CHECKPOINT = "" # 例如"/home/hmp/ChatGLM2-6B/ptuning/output/6b-pt-128-1e-2/checkpoint-100"
|
||||
|
||||
|
||||
# 本地LLM模型如ChatGLM的执行方式 CPU/GPU
|
||||
LOCAL_MODEL_DEVICE = "cpu" # 可选 "cuda"
|
||||
LOCAL_MODEL_QUANT = "FP16" # 默认 "FP16" "INT4" 启用量化INT4版本 "INT8" 启用量化INT8版本
|
||||
|
||||
|
||||
# 设置gradio的并行线程数（不需要修改）
|
||||
CONCURRENT_COUNT = 100
|
||||
|
||||
|
||||
# 是否在提交时自动清空输入框
|
||||
AUTO_CLEAR_TXT = False
|
||||
|
||||
|
||||
# 加一个live2d装饰
|
||||
ADD_WAIFU = False
|
||||
|
||||
|
||||
# 设置用户名和密码（不需要修改）（相关功能不稳定，与gradio版本和网络都相关，如果本地使用不建议加这个）
|
||||
# [("username", "password"), ("username2", "password2"), ...]
|
||||
AUTHENTICATION = [("van", "L807878712"),("林", "L807878712"),("源", "L807878712"),("欣", "L807878712"),("z", "czh123456789")]
|
||||
|
||||
|
||||
# 如果需要在二级路径下运行（常规情况下，不要修改!!）
|
||||
# （举例 CUSTOM_PATH = "/gpt_academic"，可以让软件运行在 http://ip:port/gpt_academic/ 下。）
|
||||
CUSTOM_PATH = "/"
|
||||
|
||||
|
||||
# HTTPS 秘钥和证书（不需要修改）
|
||||
SSL_KEYFILE = ""
|
||||
SSL_CERTFILE = ""
|
||||
|
||||
|
||||
# 极少数情况下，openai的官方KEY需要伴随组织编码（格式如org-xxxxxxxxxxxxxxxxxxxxxxxx）使用
|
||||
API_ORG = ""
|
||||
|
||||
|
||||
# 如果需要使用Slack Claude，使用教程详情见 request_llms/README.md
|
||||
SLACK_CLAUDE_BOT_ID = ''
|
||||
SLACK_CLAUDE_USER_TOKEN = ''
|
||||
|
||||
|
||||
# 如果需要使用AZURE（方法一：单个azure模型部署）详情请见额外文档 docs\use_azure.md
|
||||
AZURE_ENDPOINT = "https://你亲手写的api名称.openai.azure.com/"
|
||||
AZURE_API_KEY = "填入azure openai api的密钥" # 建议直接在API_KEY处填写，该选项即将被弃用
|
||||
AZURE_ENGINE = "填入你亲手写的部署名" # 读 docs\use_azure.md
|
||||
|
||||
|
||||
# 如果需要使用AZURE（方法二：多个azure模型部署+动态切换）详情请见额外文档 docs\use_azure.md
|
||||
AZURE_CFG_ARRAY = {}
|
||||
|
||||
|
||||
# 阿里云实时语音识别 配置难度较高
|
||||
# 参考 https://github.com/binary-husky/gpt_academic/blob/master/docs/use_audio.md
|
||||
ENABLE_AUDIO = False
|
||||
ALIYUN_TOKEN="" # 例如 f37f30e0f9934c34a992f6f64f7eba4f
|
||||
ALIYUN_APPKEY="" # 例如 RoPlZrM88DnAFkZK
|
||||
ALIYUN_ACCESSKEY="" # （无需填写）
|
||||
ALIYUN_SECRET="" # （无需填写）
|
||||
|
||||
|
||||
# GPT-SOVITS 文本转语音服务的运行地址（将语言模型的生成文本朗读出来）
|
||||
TTS_TYPE = "DISABLE" # EDGE_TTS / LOCAL_SOVITS_API / DISABLE
|
||||
GPT_SOVITS_URL = ""
|
||||
EDGE_TTS_VOICE = "zh-CN-XiaoxiaoNeural"
|
||||
|
||||
|
||||
# 接入讯飞星火大模型 https://console.xfyun.cn/services/iat
|
||||
XFYUN_APPID = "00000000"
|
||||
XFYUN_API_SECRET = "bbbbbbbbbbbbbbbbbbbbbbbbbbbbbbbb"
|
||||
XFYUN_API_KEY = "aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa"
|
||||
|
||||
|
||||
# 接入智谱大模型
|
||||
ZHIPUAI_API_KEY = ""
|
||||
ZHIPUAI_MODEL = "" # 此选项已废弃，不再需要填写
|
||||
|
||||
|
||||
# Claude API KEY
|
||||
ANTHROPIC_API_KEY = ""
|
||||
|
||||
|
||||
# 月之暗面 API KEY
|
||||
MOONSHOT_API_KEY = ""
|
||||
|
||||
|
||||
# 零一万物(Yi Model) API KEY
|
||||
YIMODEL_API_KEY = ""
|
||||
|
||||
|
||||
# 紫东太初大模型 https://ai-maas.wair.ac.cn
|
||||
TAICHU_API_KEY = ""
|
||||
|
||||
# Grok API KEY
|
||||
GROK_API_KEY = ""
|
||||
|
||||
# Mathpix 拥有执行PDF的OCR功能，但是需要注册账号
|
||||
MATHPIX_APPID = ""
|
||||
MATHPIX_APPKEY = ""
|
||||
|
||||
|
||||
# DOC2X的PDF解析服务，注册账号并获取API KEY: https://doc2x.noedgeai.com/login
|
||||
DOC2X_API_KEY = ""
|
||||
|
||||
|
||||
# 自定义API KEY格式
|
||||
CUSTOM_API_KEY_PATTERN = ""
|
||||
|
||||
|
||||
# Google Gemini API-Key
|
||||
GEMINI_API_KEY = ''
|
||||
|
||||
|
||||
# HUGGINGFACE的TOKEN，下载LLAMA时起作用 https://huggingface.co/docs/hub/security-tokens
|
||||
HUGGINGFACE_ACCESS_TOKEN = "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"
|
||||
|
||||
|
||||
# GROBID服务器地址（填写多个可以均衡负载），用于高质量地读取PDF文档
|
||||
# 获取方法：复制以下空间https://huggingface.co/spaces/qingxu98/grobid，设为public，然后GROBID_URL = "https://(你的hf用户名如qingxu98)-(你的填写的空间名如grobid).hf.space"
|
||||
GROBID_URLS = [
|
||||
"https://qingxu98-grobid.hf.space","https://qingxu98-grobid2.hf.space","https://qingxu98-grobid3.hf.space",
|
||||
"https://qingxu98-grobid4.hf.space","https://qingxu98-grobid5.hf.space", "https://qingxu98-grobid6.hf.space",
|
||||
"https://qingxu98-grobid7.hf.space", "https://qingxu98-grobid8.hf.space",
|
||||
]
|
||||
|
||||
|
||||
# Searxng互联网检索服务（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
|
||||
SEARXNG_URLS = [ f"https://kaletianlre-beardvs{i}dd.hf.space/" for i in range(1,5) ]
|
||||
|
||||
|
||||
# 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性，默认关闭
|
||||
ALLOW_RESET_CONFIG = False
|
||||
|
||||
|
||||
# 在使用AutoGen插件时，是否使用Docker容器运行代码
|
||||
AUTOGEN_USE_DOCKER = False
|
||||
|
||||
|
||||
# 临时的上传文件夹位置，请尽量不要修改
|
||||
PATH_PRIVATE_UPLOAD = "private_upload"
|
||||
|
||||
|
||||
# 日志文件夹的位置，请尽量不要修改
|
||||
PATH_LOGGING = "gpt_log"
|
||||
|
||||
|
||||
# 存储翻译好的arxiv论文的路径，请尽量不要修改
|
||||
ARXIV_CACHE_DIR = "gpt_log/arxiv_cache"
|
||||
|
||||
|
||||
# 除了连接OpenAI之外，还有哪些场合允许使用代理，请尽量不要修改
|
||||
WHEN_TO_USE_PROXY = ["Connect_OpenAI", "Download_LLM", "Download_Gradio_Theme", "Connect_Grobid",
|
||||
"Warmup_Modules", "Nougat_Download", "AutoGen", "Connect_OpenAI_Embedding"]
|
||||
|
||||
|
||||
# 启用插件热加载
|
||||
PLUGIN_HOT_RELOAD = False
|
||||
|
||||
|
||||
# 自定义按钮的最大数量限制
|
||||
NUM_CUSTOM_BASIC_BTN = 4
|
||||
|
||||
|
||||
# 媒体智能体的服务地址（这是一个huggingface空间，请前往huggingface复制该空间，然后把自己新的空间地址填在这里）
|
||||
DAAS_SERVER_URLS = [ f"https://niuziniu-biligpt{i}.hf.space/stream" for i in range(1,5) ]
|
||||
|
||||
|
||||
|
||||
"""
|
||||
--------------- 配置关联关系说明 ---------------
|
||||
|
||||
在线大模型配置关联关系示意图
|
||||
│
|
||||
├── "gpt-3.5-turbo" 等openai模型
|
||||
│ ├── API_KEY
|
||||
│ ├── CUSTOM_API_KEY_PATTERN（不常用）
|
||||
│ ├── API_ORG（不常用）
|
||||
│ └── API_URL_REDIRECT（不常用）
|
||||
│
|
||||
├── "azure-gpt-3.5" 等azure模型（单个azure模型，不需要动态切换）
|
||||
│ ├── API_KEY
|
||||
│ ├── AZURE_ENDPOINT
|
||||
│ ├── AZURE_API_KEY
|
||||
│ ├── AZURE_ENGINE
|
||||
│ └── API_URL_REDIRECT
|
||||
│
|
||||
├── "azure-gpt-3.5" 等azure模型（多个azure模型，需要动态切换，高优先级）
|
||||
│ └── AZURE_CFG_ARRAY
|
||||
│
|
||||
├── "spark" 星火认知大模型 spark & sparkv2
|
||||
│ ├── XFYUN_APPID
|
||||
│ ├── XFYUN_API_SECRET
|
||||
│ └── XFYUN_API_KEY
|
||||
│
|
||||
├── "claude-3-opus-20240229" 等claude模型
|
||||
│ └── ANTHROPIC_API_KEY
|
||||
│
|
||||
├── "stack-claude"
|
||||
│ ├── SLACK_CLAUDE_BOT_ID
|
||||
│ └── SLACK_CLAUDE_USER_TOKEN
|
||||
│
|
||||
├── "qianfan" 百度千帆大模型库
|
||||
│ ├── BAIDU_CLOUD_QIANFAN_MODEL
|
||||
│ ├── BAIDU_CLOUD_API_KEY
|
||||
│ └── BAIDU_CLOUD_SECRET_KEY
|
||||
│
|
||||
├── "glm-4", "glm-3-turbo", "zhipuai" 智谱AI大模型
|
||||
│ └── ZHIPUAI_API_KEY
|
||||
│
|
||||
├── "yi-34b-chat-0205", "yi-34b-chat-200k" 等零一万物(Yi Model)大模型
|
||||
│ └── YIMODEL_API_KEY
|
||||
│
|
||||
├── "qwen-turbo" 等通义千问大模型
|
||||
│ └── DASHSCOPE_API_KEY
|
||||
│
|
||||
├── "Gemini"
|
||||
│ └── GEMINI_API_KEY
|
||||
│
|
||||
└── "one-api-...(max_token=...)" 用一种更方便的方式接入one-api多模型管理界面
|
||||
├── AVAIL_LLM_MODELS
|
||||
├── API_KEY
|
||||
└── API_URL_REDIRECT
|
||||
|
||||
|
||||
本地大模型示意图
|
||||
│
|
||||
├── "chatglm4"
|
||||
├── "chatglm3"
|
||||
├── "chatglm"
|
||||
├── "chatglm_onnx"
|
||||
├── "chatglmft"
|
||||
├── "internlm"
|
||||
├── "moss"
|
||||
├── "jittorllms_pangualpha"
|
||||
├── "jittorllms_llama"
|
||||
├── "deepseekcoder"
|
||||
├── "qwen-local"
|
||||
├── RWKV的支持见Wiki
|
||||
└── "llama2"
|
||||
|
||||
|
||||
用户图形界面布局依赖关系示意图
|
||||
│
|
||||
├── CHATBOT_HEIGHT 对话窗的高度
|
||||
├── CODE_HIGHLIGHT 代码高亮
|
||||
├── LAYOUT 窗口布局
|
||||
├── DARK_MODE 暗色模式 / 亮色模式
|
||||
├── DEFAULT_FN_GROUPS 插件分类默认选项
|
||||
├── THEME 色彩主题
|
||||
├── AUTO_CLEAR_TXT 是否在提交时自动清空输入框
|
||||
├── ADD_WAIFU 加一个live2d装饰
|
||||
└── ALLOW_RESET_CONFIG 是否允许通过自然语言描述修改本页的配置，该功能具有一定的危险性
|
||||
|
||||
|
||||
插件在线服务配置依赖关系示意图
|
||||
│
|
||||
├── 互联网检索
|
||||
│ └── SEARXNG_URLS
|
||||
│
|
||||
├── 语音功能
|
||||
│ ├── ENABLE_AUDIO
|
||||
│ ├── ALIYUN_TOKEN
|
||||
│ ├── ALIYUN_APPKEY
|
||||
│ ├── ALIYUN_ACCESSKEY
|
||||
│ └── ALIYUN_SECRET
|
||||
│
|
||||
└── PDF文档精准解析
|
||||
├── GROBID_URLS
|
||||
├── MATHPIX_APPID
|
||||
└── MATHPIX_APPKEY
|
||||
|
||||
|
||||
"""
|
||||
|
||||
|
||||
|
||||
@@ -2,6 +2,7 @@ from toolbox import HotReload # HotReload 的意思是热更新，修改函数
|
||||
from toolbox import trimmed_format_exc
|
||||
from loguru import logger
|
||||
|
||||
|
||||
def get_crazy_functions():
|
||||
from crazy_functions.读文章写摘要 import 读文章写摘要
|
||||
from crazy_functions.生成函数注释 import 批量生成函数注释
|
||||
@@ -49,16 +50,8 @@ def get_crazy_functions():
|
||||
from crazy_functions.Image_Generate_Wrap import ImageGen_Wrap
|
||||
from crazy_functions.SourceCode_Comment import 注释Python项目
|
||||
from crazy_functions.SourceCode_Comment_Wrap import SourceCodeComment_Wrap
|
||||
from crazy_functions.VideoResource_GPT import 多媒体任务
|
||||
|
||||
function_plugins = {
|
||||
"多媒体智能体": {
|
||||
"Group": "智能体",
|
||||
"Color": "stop",
|
||||
"AsButton": False,
|
||||
"Info": "【仅测试】多媒体任务",
|
||||
"Function": HotReload(多媒体任务),
|
||||
},
|
||||
"虚空终端": {
|
||||
"Group": "对话|编程|学术|智能体",
|
||||
"Color": "stop",
|
||||
@@ -113,7 +106,7 @@ def get_crazy_functions():
|
||||
"Group": "学术",
|
||||
"Color": "stop",
|
||||
"AsButton": True,
|
||||
"Info": "ArXiv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
|
||||
"Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
|
||||
"Class": Arxiv_Localize, # 新一代插件需要注册Class
|
||||
},
|
||||
@@ -352,7 +345,7 @@ def get_crazy_functions():
|
||||
"ArgsReminder": r"如果有必要, 请在此处给出自定义翻译命令, 解决部分词汇翻译不准确的问题。 "
|
||||
r"例如当单词'agent'翻译不准确时, 请尝试把以下指令复制到高级参数区: "
|
||||
r'If the term "agent" is used in this section, it should be translated to "智能体". ',
|
||||
"Info": "ArXiv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
|
||||
"Info": "Arixv论文精细翻译 | 输入参数arxiv论文的ID，比如1812.10695",
|
||||
"Function": HotReload(Latex翻译中文并重新编译PDF), # 当注册Class后，Function旧接口仅会在“虚空终端”中起作用
|
||||
"Class": Arxiv_Localize, # 新一代插件需要注册Class
|
||||
},
|
||||
@@ -434,6 +427,36 @@ def get_crazy_functions():
|
||||
logger.error(trimmed_format_exc())
|
||||
logger.error("Load function plugin failed")
|
||||
|
||||
# try:
|
||||
# from crazy_functions.联网的ChatGPT import 连接网络回答问题
|
||||
|
||||
# function_plugins.update(
|
||||
# {
|
||||
# "连接网络回答问题（输入问题后点击该插件，需要访问谷歌）": {
|
||||
# "Group": "对话",
|
||||
# "Color": "stop",
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# # "Info": "连接网络回答问题（需要访问谷歌）| 输入参数是一个问题",
|
||||
# "Function": HotReload(连接网络回答问题),
|
||||
# }
|
||||
# }
|
||||
# )
|
||||
# from crazy_functions.联网的ChatGPT_bing版 import 连接bing搜索回答问题
|
||||
|
||||
# function_plugins.update(
|
||||
# {
|
||||
# "连接网络回答问题（中文Bing版，输入问题后点击该插件）": {
|
||||
# "Group": "对话",
|
||||
# "Color": "stop",
|
||||
# "AsButton": False, # 加入下拉菜单中
|
||||
# "Info": "连接网络回答问题（需要访问中文Bing）| 输入参数是一个问题",
|
||||
# "Function": HotReload(连接bing搜索回答问题),
|
||||
# }
|
||||
# }
|
||||
# )
|
||||
# except:
|
||||
# logger.error(trimmed_format_exc())
|
||||
# logger.error("Load function plugin failed")
|
||||
|
||||
try:
|
||||
from crazy_functions.SourceCode_Analyse import 解析任意code项目
|
||||
@@ -697,6 +720,12 @@ def get_crazy_functions():
|
||||
logger.error("Load function plugin failed")
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
# try:
|
||||
# from crazy_functions.高级功能函数模板 import 测试图表渲染
|
||||
# function_plugins.update({
|
||||
@@ -730,26 +759,3 @@ def get_crazy_functions():
|
||||
function_plugins[name]["Color"] = "secondary"
|
||||
|
||||
return function_plugins
|
||||
|
||||
|
||||
|
||||
|
||||
def get_multiplex_button_functions():
|
||||
"""多路复用主提交按钮的功能映射
|
||||
"""
|
||||
return {
|
||||
"常规对话":
|
||||
"",
|
||||
|
||||
"查互联网后回答":
|
||||
"查互联网后回答",
|
||||
|
||||
"多模型对话":
|
||||
"询问多个GPT模型", # 映射到上面的 `询问多个GPT模型` 插件
|
||||
|
||||
"智能召回 RAG":
|
||||
"Rag智能召回", # 映射到上面的 `Rag智能召回` 插件
|
||||
|
||||
"多媒体查询":
|
||||
"多媒体智能体", # 映射到上面的 `多媒体智能体` 插件
|
||||
}
|
||||
|
||||
62
crazy_functions/Dynamic_Load_Plugin.py
Normal file
62
crazy_functions/Dynamic_Load_Plugin.py
Normal file
@@ -0,0 +1,62 @@
|
||||
|
||||
from toolbox import get_conf, update_ui
|
||||
from crazy_functions.Image_Generate import 图片生成_DALLE2, 图片生成_DALLE3, 图片修改_DALLE2
|
||||
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
|
||||
|
||||
|
||||
|
||||
def update_js_plugin_info():
|
||||
# encode_plugin_info
|
||||
...
|
||||
|
||||
|
||||
|
||||
class ImageGen_Wrap(GptAcademicPluginTemplate):
|
||||
def __init__(self):
|
||||
"""
|
||||
请注意`execute`会执行在不同的线程中，因此您在定义和使用类变量时，应当慎之又慎！
|
||||
"""
|
||||
pass
|
||||
|
||||
def define_arg_selection_menu(self):
|
||||
"""
|
||||
定义插件的二级选项菜单
|
||||
|
||||
第一个参数，名称`main_input`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
|
||||
第二个参数，名称`advanced_arg`，参数`type`声明这是一个文本框，文本框上方显示`title`，文本框内部显示`description`，`default_value`为默认值；
|
||||
|
||||
"""
|
||||
gui_definition = {
|
||||
"main_input":
|
||||
ArgProperty(title="输入图片描述", description="需要生成图像的文本描述，尽量使用英文", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
"model_name":
|
||||
ArgProperty(title="模型", options=["DALLE2", "DALLE3"], default_value="DALLE3", description="无", type="dropdown").model_dump_json(),
|
||||
"resolution":
|
||||
ArgProperty(title="分辨率", options=["256x256(限DALLE2)", "512x512(限DALLE2)", "1024x1024", "1792x1024(限DALLE3)", "1024x1792(限DALLE3)"], default_value="1024x1024", description="无", type="dropdown").model_dump_json(),
|
||||
"quality (仅DALLE3生效)":
|
||||
ArgProperty(title="质量", options=["standard", "hd"], default_value="standard", description="无", type="dropdown").model_dump_json(),
|
||||
"style (仅DALLE3生效)":
|
||||
ArgProperty(title="风格", options=["vivid", "natural"], default_value="vivid", description="无", type="dropdown").model_dump_json(),
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
执行插件
|
||||
"""
|
||||
# 分辨率
|
||||
resolution = plugin_kwargs["resolution"].replace("(限DALLE2)", "").replace("(限DALLE3)", "")
|
||||
|
||||
if plugin_kwargs["model_name"] == "DALLE2":
|
||||
plugin_kwargs["advanced_arg"] = resolution
|
||||
yield from 图片生成_DALLE2(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
|
||||
elif plugin_kwargs["model_name"] == "DALLE3":
|
||||
quality = plugin_kwargs["quality (仅DALLE3生效)"]
|
||||
style = plugin_kwargs["style (仅DALLE3生效)"]
|
||||
plugin_kwargs["advanced_arg"] = f"{resolution}-{quality}-{style}"
|
||||
yield from 图片生成_DALLE3(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
|
||||
else:
|
||||
chatbot.append([None, "抱歉，找不到该模型"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
@@ -7,7 +7,7 @@ from bs4 import BeautifulSoup
|
||||
from functools import lru_cache
|
||||
from itertools import zip_longest
|
||||
from check_proxy import check_proxy
|
||||
from toolbox import CatchException, update_ui, get_conf, update_ui_latest_msg
|
||||
from toolbox import CatchException, update_ui, get_conf
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
||||
from request_llms.bridge_all import model_info
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
@@ -49,7 +49,7 @@ def search_optimizer(
|
||||
mutable = ["", time.time(), ""]
|
||||
llm_kwargs["temperature"] = 0.8
|
||||
try:
|
||||
query_json = predict_no_ui_long_connection(
|
||||
querys_json = predict_no_ui_long_connection(
|
||||
inputs=query,
|
||||
llm_kwargs=llm_kwargs,
|
||||
history=[],
|
||||
@@ -57,31 +57,31 @@ def search_optimizer(
|
||||
observe_window=mutable,
|
||||
)
|
||||
except Exception:
|
||||
query_json = "null"
|
||||
querys_json = "1234"
|
||||
#* 尝试解码优化后的搜索结果
|
||||
query_json = re.sub(r"```json|```", "", query_json)
|
||||
querys_json = re.sub(r"```json|```", "", querys_json)
|
||||
try:
|
||||
queries = json.loads(query_json)
|
||||
querys = json.loads(querys_json)
|
||||
except Exception:
|
||||
#* 如果解码失败,降低温度再试一次
|
||||
try:
|
||||
llm_kwargs["temperature"] = 0.4
|
||||
query_json = predict_no_ui_long_connection(
|
||||
querys_json = predict_no_ui_long_connection(
|
||||
inputs=query,
|
||||
llm_kwargs=llm_kwargs,
|
||||
history=[],
|
||||
sys_prompt=sys_prompt,
|
||||
observe_window=mutable,
|
||||
)
|
||||
query_json = re.sub(r"```json|```", "", query_json)
|
||||
queries = json.loads(query_json)
|
||||
querys_json = re.sub(r"```json|```", "", querys_json)
|
||||
querys = json.loads(querys_json)
|
||||
except Exception:
|
||||
#* 如果再次失败，直接返回原始问题
|
||||
queries = [query]
|
||||
querys = [query]
|
||||
links = []
|
||||
success = 0
|
||||
Exceptions = ""
|
||||
for q in queries:
|
||||
for q in querys:
|
||||
try:
|
||||
link = searxng_request(q, proxies, categories, searxng_url, engines=engines)
|
||||
if len(link) > 0:
|
||||
@@ -115,8 +115,7 @@ def get_auth_ip():
|
||||
|
||||
def searxng_request(query, proxies, categories='general', searxng_url=None, engines=None):
|
||||
if searxng_url is None:
|
||||
urls = get_conf("SEARXNG_URLS")
|
||||
url = random.choice(urls)
|
||||
url = get_conf("SEARXNG_URL")
|
||||
else:
|
||||
url = searxng_url
|
||||
|
||||
@@ -175,17 +174,10 @@ def scrape_text(url, proxies) -> str:
|
||||
Returns:
|
||||
str: The scraped text
|
||||
"""
|
||||
from loguru import logger
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
|
||||
'Content-Type': 'text/plain',
|
||||
}
|
||||
|
||||
# 首先采用Jina进行文本提取
|
||||
if get_conf("JINA_API_KEY"):
|
||||
try: return jina_scrape_text(url)
|
||||
except: logger.debug("Jina API 请求失败，回到旧方法")
|
||||
|
||||
try:
|
||||
response = requests.get(url, headers=headers, proxies=proxies, timeout=8)
|
||||
if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
|
||||
@@ -201,56 +193,6 @@ def scrape_text(url, proxies) -> str:
|
||||
return text
|
||||
|
||||
|
||||
def jina_scrape_text(url) -> str:
|
||||
"jina_39727421c8fa4e4fa9bd698e5211feaaDyGeVFESNrRaepWiLT0wmHYJSh-d"
|
||||
headers = {
|
||||
'User-Agent': 'Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/94.0.4606.61 Safari/537.36',
|
||||
'Content-Type': 'text/plain',
|
||||
"X-Retain-Images": "none",
|
||||
"Authorization": f'Bearer {get_conf("JINA_API_KEY")}'
|
||||
}
|
||||
response = requests.get("https://r.jina.ai/" + url, headers=headers, proxies=None, timeout=8)
|
||||
if response.status_code != 200:
|
||||
raise ValueError("Jina API 请求失败，开始尝试旧方法！" + response.text)
|
||||
if response.encoding == "ISO-8859-1": response.encoding = response.apparent_encoding
|
||||
result = response.text
|
||||
result = result.replace("\\[", "[").replace("\\]", "]").replace("\\(", "(").replace("\\)", ")")
|
||||
return response.text
|
||||
|
||||
|
||||
def internet_search_with_analysis_prompt(prompt, analysis_prompt, llm_kwargs, chatbot):
|
||||
from toolbox import get_conf
|
||||
proxies = get_conf('proxies')
|
||||
categories = 'general'
|
||||
searxng_url = None # 使用默认的searxng_url
|
||||
engines = None # 使用默认的搜索引擎
|
||||
yield from update_ui_latest_msg(lastmsg=f"检索中: {prompt} ...", chatbot=chatbot, history=[], delay=1)
|
||||
urls = searxng_request(prompt, proxies, categories, searxng_url, engines=engines)
|
||||
yield from update_ui_latest_msg(lastmsg=f"依次访问搜索到的网站 ...", chatbot=chatbot, history=[], delay=1)
|
||||
if len(urls) == 0:
|
||||
return None
|
||||
max_search_result = 5 # 最多收纳多少个网页的结果
|
||||
history = []
|
||||
for index, url in enumerate(urls[:max_search_result]):
|
||||
yield from update_ui_latest_msg(lastmsg=f"依次访问搜索到的网站: {url['link']} ...", chatbot=chatbot, history=[], delay=1)
|
||||
res = scrape_text(url['link'], proxies)
|
||||
prefix = f"第{index}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
|
||||
history.extend([prefix, res])
|
||||
i_say = f"从以上搜索结果中抽取信息，然后回答问题：{prompt} {analysis_prompt}"
|
||||
i_say, history = input_clipping( # 裁剪输入，从最长的条目开始裁剪，防止爆token
|
||||
inputs=i_say,
|
||||
history=history,
|
||||
max_token_limit=8192
|
||||
)
|
||||
gpt_say = predict_no_ui_long_connection(
|
||||
inputs=i_say,
|
||||
llm_kwargs=llm_kwargs,
|
||||
history=history,
|
||||
sys_prompt="请从搜索结果中抽取信息，对最相关的两个搜索结果进行总结，然后回答问题。",
|
||||
console_silence=False,
|
||||
)
|
||||
return gpt_say
|
||||
|
||||
@CatchException
|
||||
def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
optimizer_history = history[:-8]
|
||||
@@ -271,52 +213,23 @@ def 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
urls = search_optimizer(txt, proxies, optimizer_history, llm_kwargs, optimizer, categories, searxng_url, engines)
|
||||
history = []
|
||||
if len(urls) == 0:
|
||||
chatbot.append((f"结论：{txt}", "[Local Message] 受到限制，无法从searxng获取信息！请尝试更换搜索引擎。"))
|
||||
chatbot.append((f"结论：{txt}",
|
||||
"[Local Message] 受到限制，无法从searxng获取信息！请尝试更换搜索引擎。"))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
return
|
||||
|
||||
# ------------- < 第2步：依次访问网页 > -------------
|
||||
from concurrent.futures import ThreadPoolExecutor
|
||||
from textwrap import dedent
|
||||
max_search_result = 5 # 最多收纳多少个网页的结果
|
||||
if optimizer == "开启(增强)":
|
||||
max_search_result = 8
|
||||
template = dedent("""
|
||||
<details>
|
||||
<summary>{TITLE}</summary>
|
||||
<div class="search_result">{URL}</div>
|
||||
<div class="search_result">{CONTENT}</div>
|
||||
</details>
|
||||
""")
|
||||
|
||||
buffer = ""
|
||||
|
||||
# 创建线程池
|
||||
with ThreadPoolExecutor(max_workers=5) as executor:
|
||||
# 提交任务到线程池
|
||||
futures = []
|
||||
chatbot.append(["联网检索中 ...", None])
|
||||
for index, url in enumerate(urls[:max_search_result]):
|
||||
future = executor.submit(scrape_text, url['link'], proxies)
|
||||
futures.append((index, future, url))
|
||||
|
||||
# 处理完成的任务
|
||||
for index, future, url in futures:
|
||||
# 开始
|
||||
prefix = f"正在加载 第{index+1}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
|
||||
string_structure = template.format(TITLE=prefix, URL=url['link'], CONTENT="正在加载，请稍后 ......")
|
||||
yield from update_ui_latest_msg(lastmsg=(buffer + string_structure), chatbot=chatbot, history=history, delay=0.1) # 刷新界面
|
||||
|
||||
# 获取结果
|
||||
res = future.result()
|
||||
|
||||
# 显示结果
|
||||
prefix = f"第{index+1}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
|
||||
string_structure = template.format(TITLE=prefix, URL=url['link'], CONTENT=res[:1000] + "......")
|
||||
buffer += string_structure
|
||||
|
||||
# 更新历史
|
||||
res = scrape_text(url['link'], proxies)
|
||||
prefix = f"第{index}份搜索结果 [源自{url['source'][0]}搜索] （{url['title'][:25]}）："
|
||||
history.extend([prefix, res])
|
||||
yield from update_ui_latest_msg(lastmsg=buffer, chatbot=chatbot, history=history, delay=0.1) # 刷新界面
|
||||
res_squeeze = res.replace('\n', '...')
|
||||
chatbot[-1] = [prefix + "\n\n" + res_squeeze[:500] + "......", None]
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# ------------- < 第3步：ChatGPT综合 > -------------
|
||||
if (optimizer != "开启(增强)"):
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
import random
|
||||
|
||||
from toolbox import get_conf
|
||||
from crazy_functions.Internet_GPT import 连接网络回答问题
|
||||
from crazy_functions.plugin_template.plugin_class_template import GptAcademicPluginTemplate, ArgProperty
|
||||
@@ -20,9 +20,6 @@ class NetworkGPT_Wrap(GptAcademicPluginTemplate):
|
||||
第三个参数，名称`allow_cache`，参数`type`声明这是一个下拉菜单，下拉菜单上方显示`title`+`description`，下拉菜单的选项为`options`，`default_value`为下拉菜单默认值；
|
||||
|
||||
"""
|
||||
urls = get_conf("SEARXNG_URLS")
|
||||
url = random.choice(urls)
|
||||
|
||||
gui_definition = {
|
||||
"main_input":
|
||||
ArgProperty(title="输入问题", description="待通过互联网检索的问题，会自动读取输入框内容", default_value="", type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
@@ -33,17 +30,16 @@ class NetworkGPT_Wrap(GptAcademicPluginTemplate):
|
||||
"optimizer":
|
||||
ArgProperty(title="搜索优化", options=["关闭", "开启", "开启(增强)"], default_value="关闭", description="是否使用搜索增强。注意这可能会消耗较多token", type="dropdown").model_dump_json(),
|
||||
"searxng_url":
|
||||
ArgProperty(title="Searxng服务地址", description="输入Searxng的地址", default_value=url, type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
ArgProperty(title="Searxng服务地址", description="输入Searxng的地址", default_value=get_conf("SEARXNG_URL"), type="string").model_dump_json(), # 主输入，自动从输入框同步
|
||||
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
def execute(txt, llm_kwargs, plugin_kwargs:dict, chatbot, history, system_prompt, user_request):
|
||||
def execute(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
"""
|
||||
执行插件
|
||||
"""
|
||||
if plugin_kwargs.get("categories", None) == "网页": plugin_kwargs["categories"] = "general"
|
||||
elif plugin_kwargs.get("categories", None) == "学术论文": plugin_kwargs["categories"] = "science"
|
||||
else: plugin_kwargs["categories"] = "general"
|
||||
if plugin_kwargs["categories"] == "网页": plugin_kwargs["categories"] = "general"
|
||||
if plugin_kwargs["categories"] == "学术论文": plugin_kwargs["categories"] = "science"
|
||||
yield from 连接网络回答问题(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
from toolbox import update_ui, trimmed_format_exc, get_conf, get_log_folder, promote_file_to_downloadzone, check_repeat_upload, map_file_to_sha256
|
||||
from toolbox import CatchException, report_exception, update_ui_latest_msg, zip_result, gen_time_str
|
||||
from toolbox import CatchException, report_exception, update_ui_lastest_msg, zip_result, gen_time_str
|
||||
from functools import partial
|
||||
from loguru import logger
|
||||
|
||||
@@ -41,7 +41,7 @@ def switch_prompt(pfg, mode, more_requirement):
|
||||
return inputs_array, sys_prompt_array
|
||||
|
||||
|
||||
def descend_to_extracted_folder_if_exist(project_folder):
|
||||
def desend_to_extracted_folder_if_exist(project_folder):
|
||||
"""
|
||||
Descend into the extracted folder if it exists, otherwise return the original folder.
|
||||
|
||||
@@ -130,7 +130,7 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
|
||||
|
||||
if not txt.startswith('https://arxiv.org/abs/'):
|
||||
msg = f"解析arxiv网址失败, 期望格式例如: https://arxiv.org/abs/1707.06690。实际得到格式: {url_}。"
|
||||
yield from update_ui_latest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
|
||||
yield from update_ui_lastest_msg(msg, chatbot=chatbot, history=history) # 刷新界面
|
||||
return msg, None
|
||||
# <-------------- set format ------------->
|
||||
arxiv_id = url_.split('/abs/')[-1]
|
||||
@@ -156,16 +156,16 @@ def arxiv_download(chatbot, history, txt, allow_cache=True):
|
||||
return False
|
||||
|
||||
if os.path.exists(dst) and allow_cache:
|
||||
yield from update_ui_latest_msg(f"调用缓存 {arxiv_id}", chatbot=chatbot, history=history) # 刷新界面
|
||||
yield from update_ui_lastest_msg(f"调用缓存 {arxiv_id}", chatbot=chatbot, history=history) # 刷新界面
|
||||
success = True
|
||||
else:
|
||||
yield from update_ui_latest_msg(f"开始下载 {arxiv_id}", chatbot=chatbot, history=history) # 刷新界面
|
||||
yield from update_ui_lastest_msg(f"开始下载 {arxiv_id}", chatbot=chatbot, history=history) # 刷新界面
|
||||
success = fix_url_and_download()
|
||||
yield from update_ui_latest_msg(f"下载完成 {arxiv_id}", chatbot=chatbot, history=history) # 刷新界面
|
||||
yield from update_ui_lastest_msg(f"下载完成 {arxiv_id}", chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
|
||||
if not success:
|
||||
yield from update_ui_latest_msg(f"下载失败 {arxiv_id}", chatbot=chatbot, history=history)
|
||||
yield from update_ui_lastest_msg(f"下载失败 {arxiv_id}", chatbot=chatbot, history=history)
|
||||
raise tarfile.ReadError(f"论文下载失败 {arxiv_id}")
|
||||
|
||||
# <-------------- extract file ------------->
|
||||
@@ -288,7 +288,7 @@ def Latex英文纠错加PDF对比(txt, llm_kwargs, plugin_kwargs, chatbot, histo
|
||||
return
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = descend_to_extracted_folder_if_exist(project_folder)
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
@@ -365,7 +365,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
|
||||
try:
|
||||
txt, arxiv_id = yield from arxiv_download(chatbot, history, txt, allow_cache)
|
||||
except tarfile.ReadError as e:
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
"无法自动下载该论文的Latex源码，请前往arxiv打开此论文下载页面，点other Formats，然后download source手动下载latex源码包。接下来调用本地Latex翻译插件即可。",
|
||||
chatbot=chatbot, history=history)
|
||||
return
|
||||
@@ -404,7 +404,7 @@ def Latex翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot,
|
||||
return
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = descend_to_extracted_folder_if_exist(project_folder)
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
@@ -518,7 +518,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
|
||||
# repeat, project_folder = check_repeat_upload(file_manifest[0], hash_tag)
|
||||
|
||||
# if repeat:
|
||||
# yield from update_ui_latest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
|
||||
# yield from update_ui_lastest_msg(f"发现重复上传，请查收结果（压缩包）...", chatbot=chatbot, history=history)
|
||||
# try:
|
||||
# translate_pdf = [f for f in glob.glob(f'{project_folder}/**/merge_translate_zh.pdf', recursive=True)][0]
|
||||
# promote_file_to_downloadzone(translate_pdf, rename_file=None, chatbot=chatbot)
|
||||
@@ -531,7 +531,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
|
||||
# report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"发现重复上传，但是无法找到相关文件")
|
||||
# yield from update_ui(chatbot=chatbot, history=history)
|
||||
# else:
|
||||
# yield from update_ui_latest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
|
||||
# yield from update_ui_lastest_msg(f"未发现重复上传", chatbot=chatbot, history=history)
|
||||
|
||||
# <-------------- convert pdf into tex ------------->
|
||||
chatbot.append([f"解析项目: {txt}", "正在将PDF转换为tex项目，请耐心等待..."])
|
||||
@@ -543,7 +543,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
|
||||
return False
|
||||
|
||||
# <-------------- translate latex file into Chinese ------------->
|
||||
yield from update_ui_latest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
|
||||
yield from update_ui_lastest_msg("正在tex项目将翻译为中文...", chatbot=chatbot, history=history)
|
||||
file_manifest = [f for f in glob.glob(f'{project_folder}/**/*.tex', recursive=True)]
|
||||
if len(file_manifest) == 0:
|
||||
report_exception(chatbot, history, a=f"解析项目: {txt}", b=f"找不到任何.tex文件: {txt}")
|
||||
@@ -551,7 +551,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
|
||||
return
|
||||
|
||||
# <-------------- if is a zip/tar file ------------->
|
||||
project_folder = descend_to_extracted_folder_if_exist(project_folder)
|
||||
project_folder = desend_to_extracted_folder_if_exist(project_folder)
|
||||
|
||||
# <-------------- move latex project away from temp folder ------------->
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
@@ -559,7 +559,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
|
||||
project_folder = move_project(project_folder)
|
||||
|
||||
# <-------------- set a hash tag for repeat-checking ------------->
|
||||
with open(pj(project_folder, hash_tag + '.tag'), 'w', encoding='utf8') as f:
|
||||
with open(pj(project_folder, hash_tag + '.tag'), 'w') as f:
|
||||
f.write(hash_tag)
|
||||
f.close()
|
||||
|
||||
@@ -571,7 +571,7 @@ def PDF翻译中文并重新编译PDF(txt, llm_kwargs, plugin_kwargs, chatbot, h
|
||||
switch_prompt=_switch_prompt_)
|
||||
|
||||
# <-------------- compile PDF ------------->
|
||||
yield from update_ui_latest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
|
||||
yield from update_ui_lastest_msg("正在将翻译好的项目tex项目编译为PDF...", chatbot=chatbot, history=history)
|
||||
success = yield from 编译Latex(chatbot, history, main_file_original='merge',
|
||||
main_file_modified='merge_translate_zh', mode='translate_zh',
|
||||
work_folder_original=project_folder, work_folder_modified=project_folder,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
from toolbox import CatchException, check_packages, get_conf
|
||||
from toolbox import update_ui, update_ui_latest_msg, disable_auto_promotion
|
||||
from toolbox import update_ui, update_ui_lastest_msg, disable_auto_promotion
|
||||
from toolbox import trimmed_format_exc_markdown
|
||||
from crazy_functions.crazy_utils import get_files_from_everything
|
||||
from crazy_functions.pdf_fns.parse_pdf import get_avail_grobid_url
|
||||
@@ -47,7 +47,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
yield from 解析PDF_基于DOC2X(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request)
|
||||
return
|
||||
except:
|
||||
chatbot.append([None, f"DOC2X服务不可用，请检查报错详细。{trimmed_format_exc_markdown()}"])
|
||||
chatbot.append([None, f"DOC2X服务不可用，现在将执行效果稍差的旧版代码。{trimmed_format_exc_markdown()}"])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
if method == "GROBID":
|
||||
@@ -57,9 +57,9 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
|
||||
return
|
||||
|
||||
if method == "Classic":
|
||||
if method == "ClASSIC":
|
||||
# ------- 第三种方法，早期代码，效果不理想 -------
|
||||
yield from update_ui_latest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
|
||||
yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
|
||||
yield from 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
return
|
||||
|
||||
@@ -77,7 +77,7 @@ def 批量翻译PDF文档(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
if grobid_url is not None:
|
||||
yield from 解析PDF_基于GROBID(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, grobid_url)
|
||||
return
|
||||
yield from update_ui_latest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
|
||||
yield from update_ui_lastest_msg("GROBID服务不可用，请检查config中的GROBID_URL。作为替代，现在将执行效果稍差的旧版代码。", chatbot, history, delay=3)
|
||||
yield from 解析PDF_简单拆解(file_manifest, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt)
|
||||
return
|
||||
|
||||
|
||||
@@ -19,7 +19,7 @@ class PDF_Tran(GptAcademicPluginTemplate):
|
||||
"additional_prompt":
|
||||
ArgProperty(title="额外提示词", description="例如：对专有名词、翻译语气等方面的要求", default_value="", type="string").model_dump_json(), # 高级参数输入区，自动同步
|
||||
"pdf_parse_method":
|
||||
ArgProperty(title="PDF解析方法", options=["DOC2X", "GROBID", "Classic"], description="无", default_value="GROBID", type="dropdown").model_dump_json(),
|
||||
ArgProperty(title="PDF解析方法", options=["DOC2X", "GROBID", "ClASSIC"], description="无", default_value="GROBID", type="dropdown").model_dump_json(),
|
||||
}
|
||||
return gui_definition
|
||||
|
||||
|
||||
@@ -1,11 +1,4 @@
|
||||
import os,glob
|
||||
from typing import List
|
||||
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
|
||||
from toolbox import report_exception
|
||||
from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_latest_msg
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_lastest_msg
|
||||
from crazy_functions.crazy_utils import input_clipping
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
|
||||
@@ -14,37 +7,6 @@ MAX_HISTORY_ROUND = 5
|
||||
MAX_CONTEXT_TOKEN_LIMIT = 4096
|
||||
REMEMBER_PREVIEW = 1000
|
||||
|
||||
@CatchException
|
||||
def handle_document_upload(files: List[str], llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request, rag_worker):
|
||||
"""
|
||||
Handles document uploads by extracting text and adding it to the vector store.
|
||||
"""
|
||||
from llama_index.core import Document
|
||||
from crazy_functions.rag_fns.rag_file_support import extract_text, supports_format
|
||||
user_name = chatbot.get_user()
|
||||
checkpoint_dir = get_log_folder(user_name, plugin_name='experimental_rag')
|
||||
|
||||
for file_path in files:
|
||||
try:
|
||||
validate_path_safety(file_path, user_name)
|
||||
text = extract_text(file_path)
|
||||
if text is None:
|
||||
chatbot.append(
|
||||
[f"上传文件: {os.path.basename(file_path)}", f"文件解析失败，无法提取文本内容，请更换文件。失败原因可能为：1.文档格式过于复杂；2. 不支持的文件格式，支持的文件格式后缀有:" + ", ".join(supports_format)])
|
||||
else:
|
||||
chatbot.append(
|
||||
[f"上传文件: {os.path.basename(file_path)}", f"上传文件前50个字符为:{text[:50]}。"])
|
||||
document = Document(text=text, metadata={"source": file_path})
|
||||
rag_worker.add_documents_to_vector_store([document])
|
||||
chatbot.append([f"上传文件: {os.path.basename(file_path)}", "文件已成功添加到知识库。"])
|
||||
except Exception as e:
|
||||
report_exception(chatbot, history, a=f"处理文件: {file_path}", b=str(e))
|
||||
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
|
||||
|
||||
# Main Q&A function with document upload support
|
||||
@CatchException
|
||||
def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
|
||||
@@ -61,7 +23,6 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
|
||||
# 1. we retrieve rag worker from global context
|
||||
user_name = chatbot.get_user()
|
||||
checkpoint_dir = get_log_folder(user_name, plugin_name='experimental_rag')
|
||||
|
||||
if user_name in RAG_WORKER_REGISTER:
|
||||
rag_worker = RAG_WORKER_REGISTER[user_name]
|
||||
else:
|
||||
@@ -69,37 +30,21 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
|
||||
user_name,
|
||||
llm_kwargs,
|
||||
checkpoint_dir=checkpoint_dir,
|
||||
auto_load_checkpoint=True
|
||||
)
|
||||
|
||||
auto_load_checkpoint=True)
|
||||
current_context = f"{VECTOR_STORE_TYPE} @ {checkpoint_dir}"
|
||||
tip = "提示：输入“清空向量数据库”可以清空RAG向量数据库"
|
||||
|
||||
# 2. Handle special commands
|
||||
if os.path.exists(txt) and os.path.isdir(txt):
|
||||
project_folder = txt
|
||||
validate_path_safety(project_folder, chatbot.get_user())
|
||||
# Extract file paths from the user input
|
||||
# Assuming the user inputs file paths separated by commas after the command
|
||||
file_paths = [f for f in glob.glob(f'{project_folder}/**/*', recursive=True)]
|
||||
chatbot.append([txt, f'正在处理上传的文档 ({current_context}) ...'])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
yield from handle_document_upload(file_paths, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request, rag_worker)
|
||||
return
|
||||
|
||||
elif txt == "清空向量数据库":
|
||||
if txt == "清空向量数据库":
|
||||
chatbot.append([txt, f'正在清空 ({current_context}) ...'])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
rag_worker.purge_vector_store()
|
||||
yield from update_ui_latest_msg('已清空', chatbot, history, delay=0) # 刷新界面
|
||||
rag_worker.purge()
|
||||
yield from update_ui_lastest_msg('已清空', chatbot, history, delay=0) # 刷新界面
|
||||
return
|
||||
|
||||
# 3. Normal Q&A processing
|
||||
chatbot.append([txt, f'正在召回知识 ({current_context}) ...'])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 4. Clip history to reduce token consumption
|
||||
# 2. clip history to reduce token consumption
|
||||
# 2-1. reduce chat round
|
||||
txt_origin = txt
|
||||
|
||||
if len(history) > MAX_HISTORY_ROUND * 2:
|
||||
@@ -107,47 +52,41 @@ def Rag问答(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, u
|
||||
txt_clip, history, flags = input_clipping(txt, history, max_token_limit=MAX_CONTEXT_TOKEN_LIMIT, return_clip_flags=True)
|
||||
input_is_clipped_flag = (flags["original_input_len"] != flags["clipped_input_len"])
|
||||
|
||||
# 5. If input is clipped, add input to vector store before retrieve
|
||||
# 2-2. if input is clipped, add input to vector store before retrieve
|
||||
if input_is_clipped_flag:
|
||||
yield from update_ui_latest_msg('检测到长输入, 正在向量化 ...', chatbot, history, delay=0) # 刷新界面
|
||||
# Save input to vector store
|
||||
yield from update_ui_lastest_msg('检测到长输入, 正在向量化 ...', chatbot, history, delay=0) # 刷新界面
|
||||
# save input to vector store
|
||||
rag_worker.add_text_to_vector_store(txt_origin)
|
||||
yield from update_ui_latest_msg('向量化完成 ...', chatbot, history, delay=0) # 刷新界面
|
||||
|
||||
yield from update_ui_lastest_msg('向量化完成 ...', chatbot, history, delay=0) # 刷新界面
|
||||
if len(txt_origin) > REMEMBER_PREVIEW:
|
||||
HALF = REMEMBER_PREVIEW // 2
|
||||
HALF = REMEMBER_PREVIEW//2
|
||||
i_say_to_remember = txt[:HALF] + f" ...\n...(省略{len(txt_origin)-REMEMBER_PREVIEW}字)...\n... " + txt[-HALF:]
|
||||
if (flags["original_input_len"] - flags["clipped_input_len"]) > HALF:
|
||||
txt_clip = txt_clip + f" ...\n...(省略{len(txt_origin)-len(txt_clip)-HALF}字)...\n... " + txt[-HALF:]
|
||||
else:
|
||||
pass
|
||||
i_say = txt_clip
|
||||
else:
|
||||
i_say_to_remember = i_say = txt_clip
|
||||
else:
|
||||
i_say_to_remember = i_say = txt_clip
|
||||
|
||||
# 6. Search vector store and build prompts
|
||||
# 3. we search vector store and build prompts
|
||||
nodes = rag_worker.retrieve_from_store_with_query(i_say)
|
||||
prompt = rag_worker.build_prompt(query=i_say, nodes=nodes)
|
||||
# 7. Query language model
|
||||
if len(chatbot) != 0:
|
||||
chatbot.pop(-1) # Pop temp chat, because we are going to add them again inside `request_gpt_model_in_new_thread_with_ui_alive`
|
||||
|
||||
# 4. it is time to query llms
|
||||
if len(chatbot) != 0: chatbot.pop(-1) # pop temp chat, because we are going to add them again inside `request_gpt_model_in_new_thread_with_ui_alive`
|
||||
model_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=prompt,
|
||||
inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot,
|
||||
history=history,
|
||||
inputs=prompt, inputs_show_user=i_say,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
sys_prompt=system_prompt,
|
||||
retry_times_at_unknown_error=0
|
||||
)
|
||||
|
||||
# 8. Remember Q&A
|
||||
yield from update_ui_latest_msg(
|
||||
model_say + '</br></br>' + f'对话记忆中, 请稍等 ({current_context}) ...',
|
||||
chatbot, history, delay=0.5
|
||||
)
|
||||
# 5. remember what has been asked / answered
|
||||
yield from update_ui_lastest_msg(model_say + '</br></br>' + f'对话记忆中, 请稍等 ({current_context}) ...', chatbot, history, delay=0.5) # 刷新界面
|
||||
rag_worker.remember_qa(i_say_to_remember, model_say)
|
||||
history.extend([i_say, model_say])
|
||||
|
||||
# 9. Final UI Update
|
||||
yield from update_ui_latest_msg(model_say, chatbot, history, delay=0, msg=tip)
|
||||
yield from update_ui_lastest_msg(model_say, chatbot, history, delay=0, msg=tip) # 刷新界面
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import pickle, os, random
|
||||
from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_latest_msg
|
||||
from toolbox import CatchException, update_ui, get_conf, get_log_folder, update_ui_lastest_msg
|
||||
from crazy_functions.crazy_utils import input_clipping
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
@@ -9,7 +9,7 @@ from loguru import logger
|
||||
from typing import List
|
||||
|
||||
|
||||
SOCIAL_NETWORK_WORKER_REGISTER = {}
|
||||
SOCIAL_NETWOK_WORKER_REGISTER = {}
|
||||
|
||||
class SocialNetwork():
|
||||
def __init__(self):
|
||||
@@ -78,7 +78,7 @@ class SocialNetworkWorker(SaveAndLoad):
|
||||
for f in friend.friends_list:
|
||||
self.add_friend(f)
|
||||
msg = f"成功添加{len(friend.friends_list)}个联系人: {str(friend.friends_list)}"
|
||||
yield from update_ui_latest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=0)
|
||||
|
||||
|
||||
def run(self, txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
@@ -104,12 +104,12 @@ class SocialNetworkWorker(SaveAndLoad):
|
||||
}
|
||||
|
||||
try:
|
||||
Explanation = '\n'.join([f'{k}: {v["explain_to_llm"]}' for k, v in self.tools_to_select.items()])
|
||||
Explaination = '\n'.join([f'{k}: {v["explain_to_llm"]}' for k, v in self.tools_to_select.items()])
|
||||
class UserSociaIntention(BaseModel):
|
||||
intention_type: str = Field(
|
||||
description=
|
||||
f"The type of user intention. You must choose from {self.tools_to_select.keys()}.\n\n"
|
||||
f"Explanation:\n{Explanation}",
|
||||
f"Explaination:\n{Explaination}",
|
||||
default="SocialAdvice"
|
||||
)
|
||||
pydantic_cls_instance, err_msg = select_tool(
|
||||
@@ -118,7 +118,7 @@ class SocialNetworkWorker(SaveAndLoad):
|
||||
pydantic_cls=UserSociaIntention
|
||||
)
|
||||
except Exception as e:
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"无法理解用户意图 {err_msg}",
|
||||
chatbot=chatbot,
|
||||
history=history,
|
||||
@@ -150,10 +150,10 @@ def I人助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt,
|
||||
# 1. we retrieve worker from global context
|
||||
user_name = chatbot.get_user()
|
||||
checkpoint_dir=get_log_folder(user_name, plugin_name='experimental_rag')
|
||||
if user_name in SOCIAL_NETWORK_WORKER_REGISTER:
|
||||
social_network_worker = SOCIAL_NETWORK_WORKER_REGISTER[user_name]
|
||||
if user_name in SOCIAL_NETWOK_WORKER_REGISTER:
|
||||
social_network_worker = SOCIAL_NETWOK_WORKER_REGISTER[user_name]
|
||||
else:
|
||||
social_network_worker = SOCIAL_NETWORK_WORKER_REGISTER[user_name] = SocialNetworkWorker(
|
||||
social_network_worker = SOCIAL_NETWOK_WORKER_REGISTER[user_name] = SocialNetworkWorker(
|
||||
user_name,
|
||||
llm_kwargs,
|
||||
checkpoint_dir=checkpoint_dir,
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import os, copy, time
|
||||
from toolbox import CatchException, report_exception, update_ui, zip_result, promote_file_to_downloadzone, update_ui_latest_msg, get_conf, generate_file_link
|
||||
from toolbox import CatchException, report_exception, update_ui, zip_result, promote_file_to_downloadzone, update_ui_lastest_msg, get_conf, generate_file_link
|
||||
from shared_utils.fastapi_server import validate_path_safety
|
||||
from crazy_functions.crazy_utils import input_clipping
|
||||
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
@@ -117,7 +117,7 @@ def 注释源代码(file_manifest, project_folder, llm_kwargs, plugin_kwargs, ch
|
||||
logger.error(f"文件: {fp} 的注释结果未能成功")
|
||||
file_links = generate_file_link(preview_html_list)
|
||||
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
f"当前任务: <br/>{'<br/>'.join(tasks)}.<br/>" +
|
||||
f"剩余源文件数量: {remain}.<br/>" +
|
||||
f"已完成的文件: {sum(worker_done)}.<br/>" +
|
||||
|
||||
@@ -1,204 +0,0 @@
|
||||
import requests
|
||||
import random
|
||||
import time
|
||||
import re
|
||||
import json
|
||||
from bs4 import BeautifulSoup
|
||||
from functools import lru_cache
|
||||
from itertools import zip_longest
|
||||
from check_proxy import check_proxy
|
||||
from toolbox import CatchException, update_ui, get_conf, promote_file_to_downloadzone, update_ui_latest_msg, generate_file_link
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, input_clipping
|
||||
from request_llms.bridge_all import model_info
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
from crazy_functions.prompts.internet import SearchOptimizerPrompt, SearchAcademicOptimizerPrompt
|
||||
from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
|
||||
from textwrap import dedent
|
||||
from loguru import logger
|
||||
from pydantic import BaseModel, Field
|
||||
|
||||
class Query(BaseModel):
|
||||
search_keyword: str = Field(description="search query for video resource")
|
||||
|
||||
|
||||
class VideoResource(BaseModel):
|
||||
thought: str = Field(description="analysis of the search results based on the user's query")
|
||||
title: str = Field(description="title of the video")
|
||||
author: str = Field(description="author/uploader of the video")
|
||||
bvid: str = Field(description="unique ID of the video")
|
||||
another_failsafe_bvid: str = Field(description="provide another bvid, the other one is not working")
|
||||
|
||||
|
||||
def get_video_resource(search_keyword):
|
||||
from crazy_functions.media_fns.get_media import search_videos
|
||||
|
||||
# Search for videos and return the first result
|
||||
videos = search_videos(
|
||||
search_keyword
|
||||
)
|
||||
|
||||
# Return the first video if results exist, otherwise return None
|
||||
return videos
|
||||
|
||||
def download_video(bvid, user_name, chatbot, history):
|
||||
# from experimental_mods.get_bilibili_resource import download_bilibili
|
||||
from crazy_functions.media_fns.get_media import download_video
|
||||
# pause a while
|
||||
tic_time = 8
|
||||
for i in range(tic_time):
|
||||
yield from update_ui_latest_msg(
|
||||
lastmsg=f"即将下载音频。等待{tic_time-i}秒后自动继续, 点击“停止”键取消此操作。",
|
||||
chatbot=chatbot, history=[], delay=1)
|
||||
|
||||
# download audio
|
||||
chatbot.append((None, "下载音频, 请稍等...")); yield from update_ui(chatbot=chatbot, history=history)
|
||||
downloaded_files = yield from download_video(bvid, only_audio=True, user_name=user_name, chatbot=chatbot, history=history)
|
||||
|
||||
if len(downloaded_files) == 0:
|
||||
# failed to download audio
|
||||
return []
|
||||
|
||||
# preview
|
||||
preview_list = [promote_file_to_downloadzone(fp) for fp in downloaded_files]
|
||||
file_links = generate_file_link(preview_list)
|
||||
yield from update_ui_latest_msg(f"已完成的文件: <br/>" + file_links, chatbot=chatbot, history=history, delay=0)
|
||||
chatbot.append((None, f"即将下载视频。"))
|
||||
|
||||
# pause a while
|
||||
tic_time = 16
|
||||
for i in range(tic_time):
|
||||
yield from update_ui_latest_msg(
|
||||
lastmsg=f"即将下载视频。等待{tic_time-i}秒后自动继续, 点击“停止”键取消此操作。",
|
||||
chatbot=chatbot, history=[], delay=1)
|
||||
|
||||
# download video
|
||||
chatbot.append((None, "下载视频, 请稍等...")); yield from update_ui(chatbot=chatbot, history=history)
|
||||
downloaded_files_part2 = yield from download_video(bvid, only_audio=False, user_name=user_name, chatbot=chatbot, history=history)
|
||||
|
||||
# preview
|
||||
preview_list = [promote_file_to_downloadzone(fp) for fp in downloaded_files_part2]
|
||||
file_links = generate_file_link(preview_list)
|
||||
yield from update_ui_latest_msg(f"已完成的文件: <br/>" + file_links, chatbot=chatbot, history=history, delay=0)
|
||||
|
||||
# return
|
||||
return downloaded_files + downloaded_files_part2
|
||||
|
||||
|
||||
class Strategy(BaseModel):
|
||||
thought: str = Field(description="analysis of the user's wish, for example, can you recall the name of the resource?")
|
||||
which_methods: str = Field(description="Which method to use to find the necessary information? choose from 'method_1' and 'method_2'.")
|
||||
method_1_search_keywords: str = Field(description="Generate keywords to search the internet if you choose method 1, otherwise empty.")
|
||||
method_2_generate_keywords: str = Field(description="Generate keywords for video download engine if you choose method 2, otherwise empty.")
|
||||
|
||||
|
||||
@CatchException
|
||||
def 多媒体任务(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
user_wish: str = txt
|
||||
# query demos:
|
||||
# - "我想找一首歌，里面有句歌词是“turn your face towards the sun”"
|
||||
# - "一首歌，第一句是红豆生南国"
|
||||
# - "一首音乐，中国航天任务专用的那首"
|
||||
# - "戴森球计划在熔岩星球的音乐"
|
||||
# - "hanser的百变什么精"
|
||||
# - "打大圣残躯时的bgm"
|
||||
# - "渊下宫战斗音乐"
|
||||
|
||||
# 搜索
|
||||
chatbot.append((txt, "检索中, 请稍等..."))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
if "跳过联网搜索" not in user_wish:
|
||||
# 结构化生成
|
||||
internet_search_keyword = user_wish
|
||||
|
||||
yield from update_ui_latest_msg(lastmsg=f"发起互联网检索: {internet_search_keyword} ...", chatbot=chatbot, history=[], delay=1)
|
||||
from crazy_functions.Internet_GPT import internet_search_with_analysis_prompt
|
||||
result = yield from internet_search_with_analysis_prompt(
|
||||
prompt=internet_search_keyword,
|
||||
analysis_prompt="请根据搜索结果分析，获取用户需要找的资源的名称、作者、出处等信息。",
|
||||
llm_kwargs=llm_kwargs,
|
||||
chatbot=chatbot
|
||||
)
|
||||
|
||||
yield from update_ui_latest_msg(lastmsg=f"互联网检索结论: {result} \n\n 正在生成进一步检索方案 ...", chatbot=chatbot, history=[], delay=1)
|
||||
rf_req = dedent(f"""
|
||||
The user wish to get the following resource:
|
||||
{user_wish}
|
||||
Meanwhile, you can access another expert's opinion on the user's wish:
|
||||
{result}
|
||||
Generate search keywords (less than 5 keywords) for video download engine accordingly.
|
||||
""")
|
||||
else:
|
||||
user_wish = user_wish.replace("跳过联网搜索", "").strip()
|
||||
rf_req = dedent(f"""
|
||||
The user wish to get the following resource:
|
||||
{user_wish}
|
||||
Generate research keywords (less than 5 keywords) accordingly.
|
||||
""")
|
||||
gpt_json_io = GptJsonIO(Query)
|
||||
inputs = rf_req + gpt_json_io.format_instructions
|
||||
run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
|
||||
analyze_res = run_gpt_fn(inputs, "")
|
||||
logger.info(analyze_res)
|
||||
query: Query = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
|
||||
video_engine_keywords = query.search_keyword
|
||||
# 关键词展示
|
||||
chatbot.append((None, f"检索关键词已确认: {video_engine_keywords}。筛选中, 请稍等..."))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 获取候选资源
|
||||
candidate_dictionary: dict = get_video_resource(video_engine_keywords)
|
||||
candidate_dictionary_as_str = json.dumps(candidate_dictionary, ensure_ascii=False, indent=4)
|
||||
|
||||
# 展示候选资源
|
||||
candidate_display = "\n".join([f"{i+1}. {it['title']}" for i, it in enumerate(candidate_dictionary)])
|
||||
chatbot.append((None, f"候选:\n\n{candidate_display}"))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 结构化生成
|
||||
rf_req_2 = dedent(f"""
|
||||
The user wish to get the following resource:
|
||||
{user_wish}
|
||||
|
||||
Select the most relevant and suitable video resource from the following search results:
|
||||
{candidate_dictionary_as_str}
|
||||
|
||||
Note:
|
||||
1. The first several search video results are more likely to satisfy the user's wish.
|
||||
2. The time duration of the video should be less than 10 minutes.
|
||||
3. You should analyze the search results first, before giving your answer.
|
||||
4. Use Chinese if possible.
|
||||
5. Beside the primary video selection, give a backup video resource `bvid`.
|
||||
""")
|
||||
gpt_json_io = GptJsonIO(VideoResource)
|
||||
inputs = rf_req_2 + gpt_json_io.format_instructions
|
||||
run_gpt_fn = lambda inputs, sys_prompt: predict_no_ui_long_connection(inputs=inputs, llm_kwargs=llm_kwargs, history=[], sys_prompt=sys_prompt, observe_window=[])
|
||||
analyze_res = run_gpt_fn(inputs, "")
|
||||
logger.info(analyze_res)
|
||||
video_resource: VideoResource = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
|
||||
|
||||
# Display
|
||||
chatbot.append(
|
||||
(None,
|
||||
f"分析：{video_resource.thought}" "<br/>"
|
||||
f"选择: `{video_resource.title}`。" "<br/>"
|
||||
f"作者：{video_resource.author}"
|
||||
)
|
||||
)
|
||||
chatbot.append((None, f"下载中, 请稍等..."))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
if video_resource and video_resource.bvid:
|
||||
logger.info(video_resource)
|
||||
downloaded = yield from download_video(video_resource.bvid, chatbot.get_user(), chatbot, history)
|
||||
if not downloaded:
|
||||
chatbot.append((None, f"下载失败, 尝试备选 ..."))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
downloaded = yield from download_video(video_resource.another_failsafe_bvid, chatbot.get_user(), chatbot, history)
|
||||
|
||||
|
||||
|
||||
|
||||
|
||||
@CatchException
|
||||
def debug(bvid, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request):
|
||||
yield from download_video(bvid, chatbot.get_user(), chatbot, history)
|
||||
@@ -1,5 +1,5 @@
|
||||
from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, ProxyNetworkActivate
|
||||
from toolbox import report_exception, get_log_folder, update_ui_latest_msg, Singleton
|
||||
from toolbox import report_exception, get_log_folder, update_ui_lastest_msg, Singleton
|
||||
from crazy_functions.agent_fns.pipe import PluginMultiprocessManager, PipeCom
|
||||
from crazy_functions.agent_fns.general import AutoGenGeneral
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@ class EchoDemo(PluginMultiprocessManager):
|
||||
while True:
|
||||
msg = self.child_conn.recv() # PipeCom
|
||||
if msg.cmd == "user_input":
|
||||
# wait father user input
|
||||
# wait futher user input
|
||||
self.child_conn.send(PipeCom("show", msg.content))
|
||||
wait_success = self.subprocess_worker_wait_user_feedback(wait_msg="我准备好处理下一个问题了.")
|
||||
if not wait_success:
|
||||
|
||||
@@ -27,7 +27,7 @@ def gpt_academic_generate_oai_reply(
|
||||
llm_kwargs=llm_config,
|
||||
history=history,
|
||||
sys_prompt=self._oai_system_message[0]['content'],
|
||||
console_silence=True
|
||||
console_slience=True
|
||||
)
|
||||
assumed_done = reply.endswith('\nTERMINATE')
|
||||
return True, reply
|
||||
|
||||
@@ -10,7 +10,7 @@ from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_
|
||||
# TODO: 解决缩进问题
|
||||
|
||||
find_function_end_prompt = '''
|
||||
Below is a page of code that you need to read. This page may not yet complete, you job is to split this page to separate functions, class functions etc.
|
||||
Below is a page of code that you need to read. This page may not yet complete, you job is to split this page to sperate functions, class functions etc.
|
||||
- Provide the line number where the first visible function ends.
|
||||
- Provide the line number where the next visible function begins.
|
||||
- If there are no other functions in this page, you should simply return the line number of the last line.
|
||||
@@ -59,7 +59,7 @@ OUTPUT:
|
||||
|
||||
|
||||
|
||||
revise_function_prompt = '''
|
||||
revise_funtion_prompt = '''
|
||||
You need to read the following code, and revise the source code ({FILE_BASENAME}) according to following instructions:
|
||||
1. You should analyze the purpose of the functions (if there are any).
|
||||
2. You need to add docstring for the provided functions (if there are any).
|
||||
@@ -117,7 +117,7 @@ def zip_result(folder):
|
||||
'''
|
||||
|
||||
|
||||
revise_function_prompt_chinese = '''
|
||||
revise_funtion_prompt_chinese = '''
|
||||
您需要阅读以下代码，并根据以下说明修订源代码({FILE_BASENAME}):
|
||||
1. 如果源代码中包含函数的话, 你应该分析给定函数实现了什么功能
|
||||
2. 如果源代码中包含函数的话, 你需要为函数添加docstring, docstring必须使用中文
|
||||
@@ -188,9 +188,9 @@ class PythonCodeComment():
|
||||
self.language = language
|
||||
self.observe_window_update = observe_window_update
|
||||
if self.language == "chinese":
|
||||
self.core_prompt = revise_function_prompt_chinese
|
||||
self.core_prompt = revise_funtion_prompt_chinese
|
||||
else:
|
||||
self.core_prompt = revise_function_prompt
|
||||
self.core_prompt = revise_funtion_prompt
|
||||
self.path = None
|
||||
self.file_basename = None
|
||||
self.file_brief = ""
|
||||
@@ -222,7 +222,7 @@ class PythonCodeComment():
|
||||
history=[],
|
||||
sys_prompt="",
|
||||
observe_window=[],
|
||||
console_silence=True
|
||||
console_slience=True
|
||||
)
|
||||
|
||||
def extract_number(text):
|
||||
@@ -316,7 +316,7 @@ class PythonCodeComment():
|
||||
def tag_code(self, fn, hint):
|
||||
code = fn
|
||||
_, n_indent = self.dedent(code)
|
||||
indent_reminder = "" if n_indent == 0 else "(Reminder: as you can see, this piece of code has indent made up with {n_indent} whitespace, please preserve them in the OUTPUT.)"
|
||||
indent_reminder = "" if n_indent == 0 else "(Reminder: as you can see, this piece of code has indent made up with {n_indent} whitespace, please preseve them in the OUTPUT.)"
|
||||
brief_reminder = "" if self.file_brief == "" else f"({self.file_basename} abstract: {self.file_brief})"
|
||||
hint_reminder = "" if hint is None else f"(Reminder: do not ignore or modify code such as `{hint}`, provide complete code in the OUTPUT.)"
|
||||
self.llm_kwargs['temperature'] = 0
|
||||
@@ -333,7 +333,7 @@ class PythonCodeComment():
|
||||
history=[],
|
||||
sys_prompt="",
|
||||
observe_window=[],
|
||||
console_silence=True
|
||||
console_slience=True
|
||||
)
|
||||
|
||||
def get_code_block(reply):
|
||||
@@ -400,7 +400,7 @@ class PythonCodeComment():
|
||||
return revised
|
||||
|
||||
def begin_comment_source_code(self, chatbot=None, history=None):
|
||||
# from toolbox import update_ui_latest_msg
|
||||
# from toolbox import update_ui_lastest_msg
|
||||
assert self.path is not None
|
||||
assert '.py' in self.path # must be python source code
|
||||
# write_target = self.path + '.revised.py'
|
||||
@@ -409,10 +409,10 @@ class PythonCodeComment():
|
||||
# with open(self.path + '.revised.py', 'w+', encoding='utf8') as f:
|
||||
while True:
|
||||
try:
|
||||
# yield from update_ui_latest_msg(f"({self.file_basename}) 正在读取下一段代码片段:\n", chatbot=chatbot, history=history, delay=0)
|
||||
# yield from update_ui_lastest_msg(f"({self.file_basename}) 正在读取下一段代码片段:\n", chatbot=chatbot, history=history, delay=0)
|
||||
next_batch, line_no_start, line_no_end = self.get_next_batch()
|
||||
self.observe_window_update(f"正在处理{self.file_basename} - {line_no_start}/{len(self.full_context)}\n")
|
||||
# yield from update_ui_latest_msg(f"({self.file_basename}) 处理代码片段:\n\n{next_batch}", chatbot=chatbot, history=history, delay=0)
|
||||
# yield from update_ui_lastest_msg(f"({self.file_basename}) 处理代码片段:\n\n{next_batch}", chatbot=chatbot, history=history, delay=0)
|
||||
|
||||
hint = None
|
||||
MAX_ATTEMPT = 2
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
import os
|
||||
import threading
|
||||
from loguru import logger
|
||||
from shared_utils.char_visual_effect import scrolling_visual_effect
|
||||
from shared_utils.char_visual_effect import scolling_visual_effect
|
||||
from toolbox import update_ui, get_conf, trimmed_format_exc, get_max_token, Singleton
|
||||
|
||||
def input_clipping(inputs, history, max_token_limit, return_clip_flags=False):
|
||||
@@ -169,7 +169,6 @@ def can_multi_process(llm) -> bool:
|
||||
def default_condition(llm) -> bool:
|
||||
# legacy condition
|
||||
if llm.startswith('gpt-'): return True
|
||||
if llm.startswith('chatgpt-'): return True
|
||||
if llm.startswith('api2d-'): return True
|
||||
if llm.startswith('azure-'): return True
|
||||
if llm.startswith('spark'): return True
|
||||
@@ -256,7 +255,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
# 【第一种情况】：顺利完成
|
||||
gpt_say = predict_no_ui_long_connection(
|
||||
inputs=inputs, llm_kwargs=llm_kwargs, history=history,
|
||||
sys_prompt=sys_prompt, observe_window=mutable[index], console_silence=True
|
||||
sys_prompt=sys_prompt, observe_window=mutable[index], console_slience=True
|
||||
)
|
||||
mutable[index][2] = "已成功"
|
||||
return gpt_say
|
||||
@@ -326,7 +325,7 @@ def request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency(
|
||||
mutable[thread_index][1] = time.time()
|
||||
# 在前端打印些好玩的东西
|
||||
for thread_index, _ in enumerate(worker_done):
|
||||
print_something_really_funny = f"[ ...`{scrolling_visual_effect(mutable[thread_index][0], scroller_max_len)}`... ]"
|
||||
print_something_really_funny = f"[ ...`{scolling_visual_effect(mutable[thread_index][0], scroller_max_len)}`... ]"
|
||||
observe_win.append(print_something_really_funny)
|
||||
# 在前端打印些好玩的东西
|
||||
stat_str = ''.join([f'`{mutable[thread_index][2]}`: {obs}\n\n'
|
||||
@@ -389,11 +388,11 @@ def read_and_clean_pdf_text(fp):
|
||||
"""
|
||||
提取文本块主字体
|
||||
"""
|
||||
fsize_statistics = {}
|
||||
fsize_statiscs = {}
|
||||
for wtf in l['spans']:
|
||||
if wtf['size'] not in fsize_statistics: fsize_statistics[wtf['size']] = 0
|
||||
fsize_statistics[wtf['size']] += len(wtf['text'])
|
||||
return max(fsize_statistics, key=fsize_statistics.get)
|
||||
if wtf['size'] not in fsize_statiscs: fsize_statiscs[wtf['size']] = 0
|
||||
fsize_statiscs[wtf['size']] += len(wtf['text'])
|
||||
return max(fsize_statiscs, key=fsize_statiscs.get)
|
||||
|
||||
def ffsize_same(a,b):
|
||||
"""
|
||||
@@ -433,11 +432,11 @@ def read_and_clean_pdf_text(fp):
|
||||
|
||||
############################## <第 2 步，获取正文主字体> ##################################
|
||||
try:
|
||||
fsize_statistics = {}
|
||||
fsize_statiscs = {}
|
||||
for span in meta_span:
|
||||
if span[1] not in fsize_statistics: fsize_statistics[span[1]] = 0
|
||||
fsize_statistics[span[1]] += span[2]
|
||||
main_fsize = max(fsize_statistics, key=fsize_statistics.get)
|
||||
if span[1] not in fsize_statiscs: fsize_statiscs[span[1]] = 0
|
||||
fsize_statiscs[span[1]] += span[2]
|
||||
main_fsize = max(fsize_statiscs, key=fsize_statiscs.get)
|
||||
if REMOVE_FOOT_NOTE:
|
||||
give_up_fize_threshold = main_fsize * REMOVE_FOOT_FFSIZE_PERCENT
|
||||
except:
|
||||
@@ -610,9 +609,9 @@ class nougat_interface():
|
||||
|
||||
|
||||
def NOUGAT_parse_pdf(self, fp, chatbot, history):
|
||||
from toolbox import update_ui_latest_msg
|
||||
from toolbox import update_ui_lastest_msg
|
||||
|
||||
yield from update_ui_latest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
|
||||
yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在排队, 等待线程锁...",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
self.threadLock.acquire()
|
||||
import glob, threading, os
|
||||
@@ -620,7 +619,7 @@ class nougat_interface():
|
||||
dst = os.path.join(get_log_folder(plugin_name='nougat'), gen_time_str())
|
||||
os.makedirs(dst)
|
||||
|
||||
yield from update_ui_latest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
|
||||
yield from update_ui_lastest_msg("正在解析论文, 请稍候。进度：正在加载NOUGAT... （提示：首次运行需要花费较长时间下载NOUGAT参数）",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
command = ['nougat', '--out', os.path.abspath(dst), os.path.abspath(fp)]
|
||||
self.nougat_with_timeout(command, cwd=os.getcwd(), timeout=3600)
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from toolbox import CatchException, update_ui, update_ui_latest_msg
|
||||
from toolbox import CatchException, update_ui, update_ui_lastest_msg
|
||||
from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
@@ -13,7 +13,7 @@ class MiniGame_ASCII_Art(GptAcademicGameBaseState):
|
||||
else:
|
||||
if prompt.strip() == 'exit':
|
||||
self.delete_game = True
|
||||
yield from update_ui_latest_msg(lastmsg=f"谜底是{self.obj}，游戏结束。", chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg=f"谜底是{self.obj}，游戏结束。", chatbot=chatbot, history=history, delay=0.)
|
||||
return
|
||||
chatbot.append([prompt, ""])
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
@@ -31,12 +31,12 @@ class MiniGame_ASCII_Art(GptAcademicGameBaseState):
|
||||
self.cur_task = 'identify user guess'
|
||||
res = get_code_block(raw_res)
|
||||
history += ['', f'the answer is {self.obj}', inputs, res]
|
||||
yield from update_ui_latest_msg(lastmsg=res, chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg=res, chatbot=chatbot, history=history, delay=0.)
|
||||
|
||||
elif self.cur_task == 'identify user guess':
|
||||
if is_same_thing(self.obj, prompt, self.llm_kwargs):
|
||||
self.delete_game = True
|
||||
yield from update_ui_latest_msg(lastmsg="你猜对了！", chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg="你猜对了！", chatbot=chatbot, history=history, delay=0.)
|
||||
else:
|
||||
self.cur_task = 'identify user guess'
|
||||
yield from update_ui_latest_msg(lastmsg="猜错了，再试试，输入“exit”获取答案。", chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg="猜错了，再试试，输入“exit”获取答案。", chatbot=chatbot, history=history, delay=0.)
|
||||
@@ -63,7 +63,7 @@ prompts_terminate = """小说的前文回顾：
|
||||
"""
|
||||
|
||||
|
||||
from toolbox import CatchException, update_ui, update_ui_latest_msg
|
||||
from toolbox import CatchException, update_ui, update_ui_lastest_msg
|
||||
from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
@@ -112,7 +112,7 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
if prompt.strip() == 'exit' or prompt.strip() == '结束剧情':
|
||||
# should we terminate game here?
|
||||
self.delete_game = True
|
||||
yield from update_ui_latest_msg(lastmsg=f"游戏结束。", chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg=f"游戏结束。", chatbot=chatbot, history=history, delay=0.)
|
||||
return
|
||||
if '剧情收尾' in prompt:
|
||||
self.cur_task = 'story_terminate'
|
||||
@@ -137,8 +137,8 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
)
|
||||
self.story.append(story_paragraph)
|
||||
# # 配图
|
||||
yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
|
||||
|
||||
# # 构建后续剧情引导
|
||||
previously_on_story = ""
|
||||
@@ -171,8 +171,8 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
)
|
||||
self.story.append(story_paragraph)
|
||||
# # 配图
|
||||
yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
|
||||
|
||||
# # 构建后续剧情引导
|
||||
previously_on_story = ""
|
||||
@@ -204,8 +204,8 @@ class MiniGame_ResumeStory(GptAcademicGameBaseState):
|
||||
chatbot, history_, self.sys_prompt_
|
||||
)
|
||||
# # 配图
|
||||
yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_latest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>正在生成插图中 ...', chatbot=chatbot, history=history, delay=0.)
|
||||
yield from update_ui_lastest_msg(lastmsg=story_paragraph + '<br/>'+ self.generate_story_image(story_paragraph), chatbot=chatbot, history=history, delay=0.)
|
||||
|
||||
# terminate game
|
||||
self.delete_game = True
|
||||
|
||||
@@ -2,7 +2,7 @@ import time
|
||||
import importlib
|
||||
from toolbox import trimmed_format_exc, gen_time_str, get_log_folder
|
||||
from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, is_the_upload_folder
|
||||
from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_latest_msg
|
||||
from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_lastest_msg
|
||||
import multiprocessing
|
||||
|
||||
def get_class_name(class_string):
|
||||
|
||||
@@ -102,10 +102,10 @@ class GptJsonIO():
|
||||
logging.info(f'Repairing json：{response}')
|
||||
repair_prompt = self.generate_repair_prompt(broken_json = response, error=repr(e))
|
||||
result = self.generate_output(gpt_gen_fn(repair_prompt, self.format_instructions))
|
||||
logging.info('Repair json success.')
|
||||
logging.info('Repaire json success.')
|
||||
except Exception as e:
|
||||
# 没辙了，放弃治疗
|
||||
logging.info('Repair json fail.')
|
||||
logging.info('Repaire json fail.')
|
||||
raise JsonStringError('Cannot repair json.', str(e))
|
||||
return result
|
||||
|
||||
|
||||
@@ -3,7 +3,7 @@ import re
|
||||
import shutil
|
||||
import numpy as np
|
||||
from loguru import logger
|
||||
from toolbox import update_ui, update_ui_latest_msg, get_log_folder, gen_time_str
|
||||
from toolbox import update_ui, update_ui_lastest_msg, get_log_folder, gen_time_str
|
||||
from toolbox import get_conf, promote_file_to_downloadzone
|
||||
from crazy_functions.latex_fns.latex_toolbox import PRESERVE, TRANSFORM
|
||||
from crazy_functions.latex_fns.latex_toolbox import set_forbidden_text, set_forbidden_text_begin_end, set_forbidden_text_careful_brace
|
||||
@@ -20,7 +20,7 @@ def split_subprocess(txt, project_folder, return_dict, opts):
|
||||
"""
|
||||
break down latex file to a linked list,
|
||||
each node use a preserve flag to indicate whether it should
|
||||
be processed by GPT.
|
||||
be proccessed by GPT.
|
||||
"""
|
||||
text = txt
|
||||
mask = np.zeros(len(txt), dtype=np.uint8) + TRANSFORM
|
||||
@@ -85,14 +85,14 @@ class LatexPaperSplit():
|
||||
"""
|
||||
break down latex file to a linked list,
|
||||
each node use a preserve flag to indicate whether it should
|
||||
be processed by GPT.
|
||||
be proccessed by GPT.
|
||||
"""
|
||||
def __init__(self) -> None:
|
||||
self.nodes = None
|
||||
self.msg = "*{\\scriptsize\\textbf{警告：该PDF由GPT-Academic开源项目调用大语言模型+Latex翻译插件一键生成，" + \
|
||||
"版权归原文作者所有。翻译内容可靠性无保障，请仔细鉴别并以原文为准。" + \
|
||||
"项目Github地址 \\url{https://github.com/binary-husky/gpt_academic/}。"
|
||||
# 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加README中的QQ联系开发者）
|
||||
# 请您不要删除或修改这行警告，除非您是论文的原作者（如果您是论文原作者，欢迎加REAME中的QQ联系开发者）
|
||||
self.msg_declare = "为了防止大语言模型的意外谬误产生扩散影响，禁止移除或修改此警告。}}\\\\"
|
||||
self.title = "unknown"
|
||||
self.abstract = "unknown"
|
||||
@@ -151,7 +151,7 @@ class LatexPaperSplit():
|
||||
"""
|
||||
break down latex file to a linked list,
|
||||
each node use a preserve flag to indicate whether it should
|
||||
be processed by GPT.
|
||||
be proccessed by GPT.
|
||||
P.S. use multiprocessing to avoid timeout error
|
||||
"""
|
||||
import multiprocessing
|
||||
@@ -300,8 +300,7 @@ def Latex精细分解与转化(file_manifest, project_folder, llm_kwargs, plugin
|
||||
write_html(pfg.sp_file_contents, pfg.sp_file_result, chatbot=chatbot, project_folder=project_folder)
|
||||
|
||||
# <-------- 写出文件 ---------->
|
||||
model_name = llm_kwargs['llm_model'].replace('_', '\\_') # 替换LLM模型名称中的下划线为转义字符
|
||||
msg = f"当前大语言模型: {model_name}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
|
||||
msg = f"当前大语言模型: {llm_kwargs['llm_model']}，当前语言模型温度设定: {llm_kwargs['temperature']}。"
|
||||
final_tex = lps.merge_result(pfg.file_result, mode, msg)
|
||||
objdump((lps, pfg.file_result, mode, msg), file=pj(project_folder,'merge_result.pkl'))
|
||||
|
||||
@@ -351,42 +350,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
max_try = 32
|
||||
chatbot.append([f"正在编译PDF文档", f'编译已经开始。当前工作路径为{work_folder}，如果程序停顿5分钟以上，请直接去该路径下取回翻译结果，或者重启之后再度尝试 ...']); yield from update_ui(chatbot=chatbot, history=history)
|
||||
chatbot.append([f"正在编译PDF文档", '...']); yield from update_ui(chatbot=chatbot, history=history); time.sleep(1); chatbot[-1] = list(chatbot[-1]) # 刷新界面
|
||||
yield from update_ui_latest_msg('编译已经开始...', chatbot, history) # 刷新Gradio前端界面
|
||||
# 检查是否需要使用xelatex
|
||||
def check_if_need_xelatex(tex_path):
|
||||
try:
|
||||
with open(tex_path, 'r', encoding='utf-8', errors='replace') as f:
|
||||
content = f.read(5000)
|
||||
# 检查是否有使用xelatex的宏包
|
||||
need_xelatex = any(
|
||||
pkg in content
|
||||
for pkg in ['fontspec', 'xeCJK', 'xetex', 'unicode-math', 'xltxtra', 'xunicode']
|
||||
)
|
||||
if need_xelatex:
|
||||
logger.info(f"检测到宏包需要xelatex编译, 切换至xelatex编译")
|
||||
else:
|
||||
logger.info(f"未检测到宏包需要xelatex编译, 使用pdflatex编译")
|
||||
return need_xelatex
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
# 根据编译器类型返回编译命令
|
||||
def get_compile_command(compiler, filename):
|
||||
compile_command = f'{compiler} -interaction=batchmode -file-line-error {filename}.tex'
|
||||
logger.info('Latex 编译指令: ' + compile_command)
|
||||
return compile_command
|
||||
|
||||
# 确定使用的编译器
|
||||
compiler = 'pdflatex'
|
||||
if check_if_need_xelatex(pj(work_folder_modified, f'{main_file_modified}.tex')):
|
||||
logger.info("检测到宏包需要xelatex编译，切换至xelatex编译")
|
||||
# Check if xelatex is installed
|
||||
try:
|
||||
import subprocess
|
||||
subprocess.run(['xelatex', '--version'], capture_output=True, check=True)
|
||||
compiler = 'xelatex'
|
||||
except (subprocess.CalledProcessError, FileNotFoundError):
|
||||
raise RuntimeError("检测到需要使用xelatex编译，但系统中未安装xelatex。请先安装texlive或其他提供xelatex的LaTeX发行版。")
|
||||
yield from update_ui_lastest_msg('编译已经开始...', chatbot, history) # 刷新Gradio前端界面
|
||||
|
||||
while True:
|
||||
import os
|
||||
@@ -396,36 +360,36 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
shutil.copyfile(may_exist_bbl, target_bbl)
|
||||
|
||||
# https://stackoverflow.com/questions/738755/dont-make-me-manually-abort-a-latex-compile-when-theres-an-error
|
||||
yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译原始PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
|
||||
|
||||
yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译转化后的PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
|
||||
|
||||
if ok and os.path.exists(pj(work_folder_modified, f'{main_file_modified}.pdf')):
|
||||
# 只有第二步成功，才能继续下面的步骤
|
||||
yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history) # 刷新Gradio前端界面
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译BibTex ...', chatbot, history) # 刷新Gradio前端界面
|
||||
if not os.path.exists(pj(work_folder_original, f'{main_file_original}.bbl')):
|
||||
ok = compile_latex_with_timeout(f'bibtex {main_file_original}.aux', work_folder_original)
|
||||
if not os.path.exists(pj(work_folder_modified, f'{main_file_modified}.bbl')):
|
||||
ok = compile_latex_with_timeout(f'bibtex {main_file_modified}.aux', work_folder_modified)
|
||||
|
||||
yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
|
||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
|
||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_original), work_folder_original)
|
||||
ok = compile_latex_with_timeout(get_compile_command(compiler, main_file_modified), work_folder_modified)
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 编译文献交叉引用 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_original}.tex', work_folder_original)
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error {main_file_modified}.tex', work_folder_modified)
|
||||
|
||||
if mode!='translate_zh':
|
||||
yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 使用latexdiff生成论文转化前后对比 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
logger.info( f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex')
|
||||
ok = compile_latex_with_timeout(f'latexdiff --encoding=utf8 --append-safecmd=subfile {work_folder_original}/{main_file_original}.tex {work_folder_modified}/{main_file_modified}.tex --flatten > {work_folder}/merge_diff.tex', os.getcwd())
|
||||
|
||||
yield from update_ui_latest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||
ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
|
||||
yield from update_ui_lastest_msg(f'尝试第 {n_fix}/{max_try} 次编译, 正在编译对比PDF ...', chatbot, history) # 刷新Gradio前端界面
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
|
||||
ok = compile_latex_with_timeout(f'bibtex merge_diff.aux', work_folder)
|
||||
ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
|
||||
ok = compile_latex_with_timeout(get_compile_command(compiler, 'merge_diff'), work_folder)
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
|
||||
ok = compile_latex_with_timeout(f'pdflatex -interaction=batchmode -file-line-error merge_diff.tex', work_folder)
|
||||
|
||||
# <---------- 检查结果 ----------->
|
||||
results_ = ""
|
||||
@@ -435,13 +399,13 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
results_ += f"原始PDF编译是否成功: {original_pdf_success};"
|
||||
results_ += f"转化PDF编译是否成功: {modified_pdf_success};"
|
||||
results_ += f"对比PDF编译是否成功: {diff_pdf_success};"
|
||||
yield from update_ui_latest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
|
||||
yield from update_ui_lastest_msg(f'第{n_fix}编译结束:<br/>{results_}...', chatbot, history) # 刷新Gradio前端界面
|
||||
|
||||
if diff_pdf_success:
|
||||
result_pdf = pj(work_folder_modified, f'merge_diff.pdf') # get pdf path
|
||||
promote_file_to_downloadzone(result_pdf, rename_file=None, chatbot=chatbot) # promote file to web UI
|
||||
if modified_pdf_success:
|
||||
yield from update_ui_latest_msg(f'转化PDF编译已经成功, 正在尝试生成对比PDF, 请稍候 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
yield from update_ui_lastest_msg(f'转化PDF编译已经成功, 正在尝试生成对比PDF, 请稍候 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
result_pdf = pj(work_folder_modified, f'{main_file_modified}.pdf') # get pdf path
|
||||
origin_pdf = pj(work_folder_original, f'{main_file_original}.pdf') # get pdf path
|
||||
if os.path.exists(pj(work_folder, '..', 'translation')):
|
||||
@@ -472,7 +436,7 @@ def 编译Latex(chatbot, history, main_file_original, main_file_modified, work_f
|
||||
work_folder_modified=work_folder_modified,
|
||||
fixed_line=fixed_line
|
||||
)
|
||||
yield from update_ui_latest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
yield from update_ui_lastest_msg(f'由于最为关键的转化PDF编译失败, 将根据报错信息修正tex源文件并重试, 当前报错的latex代码处于第{buggy_lines}行 ...', chatbot, history) # 刷新Gradio前端界面
|
||||
if not can_retry: break
|
||||
|
||||
return False # 失败啦
|
||||
|
||||
@@ -168,7 +168,7 @@ def set_forbidden_text(text, mask, pattern, flags=0):
|
||||
def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
|
||||
"""
|
||||
Move area out of preserve area (make text editable for GPT)
|
||||
count the number of the braces so as to catch complete text area.
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\begin{abstract} blablablablablabla. \end{abstract}
|
||||
"""
|
||||
@@ -188,7 +188,7 @@ def reverse_forbidden_text(text, mask, pattern, flags=0, forbid_wrapper=True):
|
||||
def set_forbidden_text_careful_brace(text, mask, pattern, flags=0):
|
||||
"""
|
||||
Add a preserve text area in this paper (text become untouchable for GPT).
|
||||
count the number of the braces so as to catch complete text area.
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\caption{blablablablabla\texbf{blablabla}blablabla.}
|
||||
"""
|
||||
@@ -214,7 +214,7 @@ def reverse_forbidden_text_careful_brace(
|
||||
):
|
||||
"""
|
||||
Move area out of preserve area (make text editable for GPT)
|
||||
count the number of the braces so as to catch complete text area.
|
||||
count the number of the braces so as to catch compelete text area.
|
||||
e.g.
|
||||
\caption{blablablablabla\texbf{blablabla}blablabla.}
|
||||
"""
|
||||
@@ -287,23 +287,23 @@ def find_main_tex_file(file_manifest, mode):
|
||||
在多Tex文档中，寻找主文件，必须包含documentclass，返回找到的第一个。
|
||||
P.S. 但愿没人把latex模板放在里面传进来 (6.25 加入判定latex模板的代码)
|
||||
"""
|
||||
candidates = []
|
||||
canidates = []
|
||||
for texf in file_manifest:
|
||||
if os.path.basename(texf).startswith("merge"):
|
||||
continue
|
||||
with open(texf, "r", encoding="utf8", errors="ignore") as f:
|
||||
file_content = f.read()
|
||||
if r"\documentclass" in file_content:
|
||||
candidates.append(texf)
|
||||
canidates.append(texf)
|
||||
else:
|
||||
continue
|
||||
|
||||
if len(candidates) == 0:
|
||||
if len(canidates) == 0:
|
||||
raise RuntimeError("无法找到一个主Tex文件（包含documentclass关键字）")
|
||||
elif len(candidates) == 1:
|
||||
return candidates[0]
|
||||
else: # if len(candidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
|
||||
candidates_score = []
|
||||
elif len(canidates) == 1:
|
||||
return canidates[0]
|
||||
else: # if len(canidates) >= 2 通过一些Latex模板中常见（但通常不会出现在正文）的单词，对不同latex源文件扣分，取评分最高者返回
|
||||
canidates_score = []
|
||||
# 给出一些判定模板文档的词作为扣分项
|
||||
unexpected_words = [
|
||||
"\\LaTeX",
|
||||
@@ -316,19 +316,19 @@ def find_main_tex_file(file_manifest, mode):
|
||||
"reviewers",
|
||||
]
|
||||
expected_words = ["\\input", "\\ref", "\\cite"]
|
||||
for texf in candidates:
|
||||
candidates_score.append(0)
|
||||
for texf in canidates:
|
||||
canidates_score.append(0)
|
||||
with open(texf, "r", encoding="utf8", errors="ignore") as f:
|
||||
file_content = f.read()
|
||||
file_content = rm_comments(file_content)
|
||||
for uw in unexpected_words:
|
||||
if uw in file_content:
|
||||
candidates_score[-1] -= 1
|
||||
canidates_score[-1] -= 1
|
||||
for uw in expected_words:
|
||||
if uw in file_content:
|
||||
candidates_score[-1] += 1
|
||||
select = np.argmax(candidates_score) # 取评分最高者返回
|
||||
return candidates[select]
|
||||
canidates_score[-1] += 1
|
||||
select = np.argmax(canidates_score) # 取评分最高者返回
|
||||
return canidates[select]
|
||||
|
||||
|
||||
def rm_comments(main_file):
|
||||
@@ -374,7 +374,7 @@ def find_tex_file_ignore_case(fp):
|
||||
|
||||
def merge_tex_files_(project_foler, main_file, mode):
|
||||
"""
|
||||
Merge Tex project recursively
|
||||
Merge Tex project recrusively
|
||||
"""
|
||||
main_file = rm_comments(main_file)
|
||||
for s in reversed([q for q in re.finditer(r"\\input\{(.*?)\}", main_file, re.M)]):
|
||||
@@ -429,7 +429,7 @@ def find_title_and_abs(main_file):
|
||||
|
||||
def merge_tex_files(project_foler, main_file, mode):
|
||||
"""
|
||||
Merge Tex project recursively
|
||||
Merge Tex project recrusively
|
||||
P.S. 顺便把CTEX塞进去以支持中文
|
||||
P.S. 顺便把Latex的注释去除
|
||||
"""
|
||||
|
||||
@@ -1,43 +0,0 @@
|
||||
from toolbox import update_ui, get_conf, promote_file_to_downloadzone, update_ui_latest_msg, generate_file_link
|
||||
from shared_utils.docker_as_service_api import stream_daas
|
||||
from shared_utils.docker_as_service_api import DockerServiceApiComModel
|
||||
import random
|
||||
|
||||
def download_video(video_id, only_audio, user_name, chatbot, history):
|
||||
from toolbox import get_log_folder
|
||||
chatbot.append([None, "Processing..."])
|
||||
yield from update_ui(chatbot, history)
|
||||
client_command = f'{video_id} --audio-only' if only_audio else video_id
|
||||
server_urls = get_conf('DAAS_SERVER_URLS')
|
||||
server_url = random.choice(server_urls)
|
||||
docker_service_api_com_model = DockerServiceApiComModel(client_command=client_command)
|
||||
save_file_dir = get_log_folder(user_name, plugin_name='media_downloader')
|
||||
for output_manifest in stream_daas(docker_service_api_com_model, server_url, save_file_dir):
|
||||
status_buf = ""
|
||||
status_buf += "DaaS message: \n\n"
|
||||
status_buf += output_manifest['server_message'].replace('\n', '<br/>')
|
||||
status_buf += "\n\n"
|
||||
status_buf += "DaaS standard error: \n\n"
|
||||
status_buf += output_manifest['server_std_err'].replace('\n', '<br/>')
|
||||
status_buf += "\n\n"
|
||||
status_buf += "DaaS standard output: \n\n"
|
||||
status_buf += output_manifest['server_std_out'].replace('\n', '<br/>')
|
||||
status_buf += "\n\n"
|
||||
status_buf += "DaaS file attach: \n\n"
|
||||
status_buf += str(output_manifest['server_file_attach'])
|
||||
yield from update_ui_latest_msg(status_buf, chatbot, history)
|
||||
|
||||
return output_manifest['server_file_attach']
|
||||
|
||||
|
||||
def search_videos(keywords):
|
||||
from toolbox import get_log_folder
|
||||
client_command = keywords
|
||||
server_urls = get_conf('DAAS_SERVER_URLS')
|
||||
server_url = random.choice(server_urls)
|
||||
server_url = server_url.replace('stream', 'search')
|
||||
docker_service_api_com_model = DockerServiceApiComModel(client_command=client_command)
|
||||
save_file_dir = get_log_folder("default_user", plugin_name='media_downloader')
|
||||
for output_manifest in stream_daas(docker_service_api_com_model, server_url, save_file_dir):
|
||||
return output_manifest['server_message']
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import List
|
||||
from toolbox import update_ui_latest_msg, disable_auto_promotion
|
||||
from toolbox import update_ui_lastest_msg, disable_auto_promotion
|
||||
from toolbox import CatchException, update_ui, get_conf, select_api_key, get_log_folder
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
|
||||
|
||||
@@ -113,7 +113,7 @@ def translate_pdf(article_dict, llm_kwargs, chatbot, fp, generated_conclusion_fi
|
||||
return [txt]
|
||||
else:
|
||||
# raw_token_num > TOKEN_LIMIT_PER_FRAGMENT
|
||||
# find a smooth token limit to achieve even separation
|
||||
# find a smooth token limit to achieve even seperation
|
||||
count = int(math.ceil(raw_token_num / TOKEN_LIMIT_PER_FRAGMENT))
|
||||
token_limit_smooth = raw_token_num // count + count
|
||||
return breakdown_text_to_satisfy_token_limit(txt, limit=token_limit_smooth, llm_model=llm_kwargs['llm_model'])
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import os
|
||||
from toolbox import CatchException, report_exception, get_log_folder, gen_time_str, check_packages
|
||||
from toolbox import update_ui, promote_file_to_downloadzone, update_ui_latest_msg, disable_auto_promotion
|
||||
from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
|
||||
from toolbox import write_history_to_file, promote_file_to_downloadzone, get_conf, extract_archive
|
||||
from crazy_functions.pdf_fns.parse_pdf import parse_pdf, translate_pdf
|
||||
|
||||
|
||||
@@ -6,128 +6,75 @@ from crazy_functions.crazy_utils import get_files_from_everything
|
||||
from shared_utils.colorful import *
|
||||
from loguru import logger
|
||||
import os
|
||||
import requests
|
||||
import time
|
||||
|
||||
|
||||
def retry_request(max_retries=3, delay=3):
|
||||
"""
|
||||
Decorator for retrying HTTP requests
|
||||
Args:
|
||||
max_retries: Maximum number of retry attempts
|
||||
delay: Delay between retries in seconds
|
||||
"""
|
||||
|
||||
def decorator(func):
|
||||
def wrapper(*args, **kwargs):
|
||||
for attempt in range(max_retries):
|
||||
try:
|
||||
return func(*args, **kwargs)
|
||||
except Exception as e:
|
||||
if attempt < max_retries - 1:
|
||||
logger.error(
|
||||
f"Request failed, retrying... ({attempt + 1}/{max_retries}) Error: {e}"
|
||||
def refresh_key(doc2x_api_key):
|
||||
import requests, json
|
||||
url = "https://api.doc2x.noedgeai.com/api/token/refresh"
|
||||
res = requests.post(
|
||||
url,
|
||||
headers={"Authorization": "Bearer " + doc2x_api_key}
|
||||
)
|
||||
time.sleep(delay)
|
||||
continue
|
||||
raise e
|
||||
return None
|
||||
res_json = []
|
||||
if res.status_code == 200:
|
||||
decoded = res.content.decode("utf-8")
|
||||
res_json = json.loads(decoded)
|
||||
doc2x_api_key = res_json['data']['token']
|
||||
else:
|
||||
raise RuntimeError(format("[ERROR] status code: %d, body: %s" % (res.status_code, res.text)))
|
||||
return doc2x_api_key
|
||||
|
||||
return wrapper
|
||||
|
||||
return decorator
|
||||
|
||||
|
||||
@retry_request()
|
||||
def make_request(method, url, **kwargs):
|
||||
"""
|
||||
Make HTTP request with retry mechanism
|
||||
"""
|
||||
return requests.request(method, url, **kwargs)
|
||||
|
||||
|
||||
def doc2x_api_response_status(response, uid=""):
|
||||
"""
|
||||
Check the status of Doc2x API response
|
||||
Args:
|
||||
response_data: Response object from Doc2x API
|
||||
"""
|
||||
response_json = response.json()
|
||||
response_data = response_json.get("data", {})
|
||||
code = response_json.get("code", "Unknown")
|
||||
meg = response_data.get("message", response_json)
|
||||
trace_id = response.headers.get("trace-id", "Failed to get trace-id")
|
||||
if response.status_code != 200:
|
||||
raise RuntimeError(
|
||||
f"Doc2x return an error:\nTrace ID: {trace_id} {uid}\n{response.status_code} - {response_json}"
|
||||
)
|
||||
if code in ["parse_page_limit_exceeded", "parse_concurrency_limit"]:
|
||||
raise RuntimeError(
|
||||
f"Reached the limit of Doc2x:\nTrace ID: {trace_id} {uid}\n{code} - {meg}"
|
||||
)
|
||||
if code not in ["ok", "success"]:
|
||||
raise RuntimeError(
|
||||
f"Doc2x return an error:\nTrace ID: {trace_id} {uid}\n{code} - {meg}"
|
||||
)
|
||||
return response_data
|
||||
|
||||
|
||||
def 解析PDF_DOC2X_转Latex(pdf_file_path):
|
||||
zip_file_path, unzipped_folder = 解析PDF_DOC2X(pdf_file_path, format="tex")
|
||||
zip_file_path, unzipped_folder = 解析PDF_DOC2X(pdf_file_path, format='tex')
|
||||
return unzipped_folder
|
||||
|
||||
|
||||
def 解析PDF_DOC2X(pdf_file_path, format="tex"):
|
||||
def 解析PDF_DOC2X(pdf_file_path, format='tex'):
|
||||
"""
|
||||
format: 'tex', 'md', 'docx'
|
||||
"""
|
||||
|
||||
DOC2X_API_KEY = get_conf("DOC2X_API_KEY")
|
||||
import requests, json, os
|
||||
DOC2X_API_KEY = get_conf('DOC2X_API_KEY')
|
||||
latex_dir = get_log_folder(plugin_name="pdf_ocr_latex")
|
||||
markdown_dir = get_log_folder(plugin_name="pdf_ocr")
|
||||
doc2x_api_key = DOC2X_API_KEY
|
||||
|
||||
# < ------ 第1步：预上传获取URL，然后上传文件 ------ >
|
||||
logger.info("Doc2x 上传文件：预上传获取URL")
|
||||
res = make_request(
|
||||
"POST",
|
||||
"https://v2.doc2x.noedgeai.com/api/v2/parse/preupload",
|
||||
headers={"Authorization": "Bearer " + doc2x_api_key},
|
||||
timeout=15,
|
||||
)
|
||||
res_data = doc2x_api_response_status(res)
|
||||
upload_url = res_data["url"]
|
||||
uuid = res_data["uid"]
|
||||
|
||||
logger.info("Doc2x 上传文件：上传文件")
|
||||
with open(pdf_file_path, "rb") as file:
|
||||
res = make_request("PUT", upload_url, data=file, timeout=60)
|
||||
res.raise_for_status()
|
||||
# < ------ 第1步：上传 ------ >
|
||||
logger.info("Doc2x 第1步：上传")
|
||||
with open(pdf_file_path, 'rb') as file:
|
||||
res = requests.post(
|
||||
"https://v2.doc2x.noedgeai.com/api/v2/parse/pdf",
|
||||
headers={"Authorization": "Bearer " + doc2x_api_key},
|
||||
data=file
|
||||
)
|
||||
# res_json = []
|
||||
if res.status_code == 200:
|
||||
res_json = res.json()
|
||||
else:
|
||||
raise RuntimeError(f"Doc2x return an error: {res.json()}")
|
||||
uuid = res_json['data']['uid']
|
||||
|
||||
# < ------ 第2步：轮询等待 ------ >
|
||||
logger.info("Doc2x 处理文件中：轮询等待")
|
||||
params = {"uid": uuid}
|
||||
max_attempts = 60
|
||||
attempt = 0
|
||||
while attempt < max_attempts:
|
||||
res = make_request(
|
||||
"GET",
|
||||
"https://v2.doc2x.noedgeai.com/api/v2/parse/status",
|
||||
logger.info("Doc2x 第2步：轮询等待")
|
||||
params = {'uid': uuid}
|
||||
while True:
|
||||
res = requests.get(
|
||||
'https://v2.doc2x.noedgeai.com/api/v2/parse/status',
|
||||
headers={"Authorization": "Bearer " + doc2x_api_key},
|
||||
params=params,
|
||||
timeout=15,
|
||||
params=params
|
||||
)
|
||||
res_data = doc2x_api_response_status(res)
|
||||
if res_data["status"] == "success":
|
||||
res_json = res.json()
|
||||
if res_json['data']['status'] == "success":
|
||||
break
|
||||
elif res_data["status"] == "processing":
|
||||
time.sleep(5)
|
||||
logger.info(f"Doc2x is processing at {res_data['progress']}%")
|
||||
attempt += 1
|
||||
else:
|
||||
raise RuntimeError(f"Doc2x return an error: {res_data}")
|
||||
if attempt >= max_attempts:
|
||||
raise RuntimeError("Doc2x processing timeout after maximum attempts")
|
||||
elif res_json['data']['status'] == "processing":
|
||||
time.sleep(3)
|
||||
logger.info(f"Doc2x is processing at {res_json['data']['progress']}%")
|
||||
elif res_json['data']['status'] == "failed":
|
||||
raise RuntimeError(f"Doc2x return an error: {res_json}")
|
||||
|
||||
|
||||
# < ------ 第3步：提交转化 ------ >
|
||||
logger.info("Doc2x 第3步：提交转化")
|
||||
@@ -137,44 +84,42 @@ def 解析PDF_DOC2X(pdf_file_path, format="tex"):
|
||||
"formula_mode": "dollar",
|
||||
"filename": "output"
|
||||
}
|
||||
res = make_request(
|
||||
"POST",
|
||||
"https://v2.doc2x.noedgeai.com/api/v2/convert/parse",
|
||||
res = requests.post(
|
||||
'https://v2.doc2x.noedgeai.com/api/v2/convert/parse',
|
||||
headers={"Authorization": "Bearer " + doc2x_api_key},
|
||||
json=data,
|
||||
timeout=15,
|
||||
json=data
|
||||
)
|
||||
doc2x_api_response_status(res, uid=f"uid: {uuid}")
|
||||
if res.status_code == 200:
|
||||
res_json = res.json()
|
||||
else:
|
||||
raise RuntimeError(f"Doc2x return an error: {res.json()}")
|
||||
|
||||
|
||||
# < ------ 第4步：等待结果 ------ >
|
||||
logger.info("Doc2x 第4步：等待结果")
|
||||
params = {"uid": uuid}
|
||||
max_attempts = 36
|
||||
attempt = 0
|
||||
while attempt < max_attempts:
|
||||
res = make_request(
|
||||
"GET",
|
||||
"https://v2.doc2x.noedgeai.com/api/v2/convert/parse/result",
|
||||
params = {'uid': uuid}
|
||||
while True:
|
||||
res = requests.get(
|
||||
'https://v2.doc2x.noedgeai.com/api/v2/convert/parse/result',
|
||||
headers={"Authorization": "Bearer " + doc2x_api_key},
|
||||
params=params,
|
||||
timeout=15,
|
||||
params=params
|
||||
)
|
||||
res_data = doc2x_api_response_status(res, uid=f"uid: {uuid}")
|
||||
if res_data["status"] == "success":
|
||||
res_json = res.json()
|
||||
if res_json['data']['status'] == "success":
|
||||
break
|
||||
elif res_data["status"] == "processing":
|
||||
elif res_json['data']['status'] == "processing":
|
||||
time.sleep(3)
|
||||
logger.info("Doc2x still processing to convert file")
|
||||
attempt += 1
|
||||
if attempt >= max_attempts:
|
||||
raise RuntimeError("Doc2x conversion timeout after maximum attempts")
|
||||
logger.info(f"Doc2x still processing")
|
||||
elif res_json['data']['status'] == "failed":
|
||||
raise RuntimeError(f"Doc2x return an error: {res_json}")
|
||||
|
||||
|
||||
# < ------ 第5步：最后的处理 ------ >
|
||||
logger.info("Doc2x 第5步：下载转换后的文件")
|
||||
logger.info("Doc2x 第5步：最后的处理")
|
||||
|
||||
if format == "tex":
|
||||
if format=='tex':
|
||||
target_path = latex_dir
|
||||
if format == "md":
|
||||
if format=='md':
|
||||
target_path = markdown_dir
|
||||
os.makedirs(target_path, exist_ok=True)
|
||||
|
||||
@@ -182,18 +127,17 @@ def 解析PDF_DOC2X(pdf_file_path, format="tex"):
|
||||
# < ------ 下载 ------ >
|
||||
for attempt in range(max_attempt):
|
||||
try:
|
||||
result_url = res_data["url"]
|
||||
res = make_request("GET", result_url, timeout=60)
|
||||
zip_path = os.path.join(target_path, gen_time_str() + ".zip")
|
||||
result_url = res_json['data']['url']
|
||||
res = requests.get(result_url)
|
||||
zip_path = os.path.join(target_path, gen_time_str() + '.zip')
|
||||
unzip_path = os.path.join(target_path, gen_time_str())
|
||||
if res.status_code == 200:
|
||||
with open(zip_path, "wb") as f:
|
||||
f.write(res.content)
|
||||
with open(zip_path, "wb") as f: f.write(res.content)
|
||||
else:
|
||||
raise RuntimeError(f"Doc2x return an error: {res.json()}")
|
||||
except Exception as e:
|
||||
if attempt < max_attempt - 1:
|
||||
logger.error(f"Failed to download uid = {uuid} file, retrying... {e}")
|
||||
logger.error(f"Failed to download latex file, retrying... {e}")
|
||||
time.sleep(3)
|
||||
continue
|
||||
else:
|
||||
@@ -201,27 +145,18 @@ def 解析PDF_DOC2X(pdf_file_path, format="tex"):
|
||||
|
||||
# < ------ 解压 ------ >
|
||||
import zipfile
|
||||
with zipfile.ZipFile(zip_path, "r") as zip_ref:
|
||||
with zipfile.ZipFile(zip_path, 'r') as zip_ref:
|
||||
zip_ref.extractall(unzip_path)
|
||||
return zip_path, unzip_path
|
||||
|
||||
|
||||
def 解析PDF_DOC2X_单文件(
|
||||
fp,
|
||||
project_folder,
|
||||
llm_kwargs,
|
||||
plugin_kwargs,
|
||||
chatbot,
|
||||
history,
|
||||
system_prompt,
|
||||
DOC2X_API_KEY,
|
||||
user_request,
|
||||
):
|
||||
def 解析PDF_DOC2X_单文件(fp, project_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, DOC2X_API_KEY, user_request):
|
||||
|
||||
def pdf2markdown(filepath):
|
||||
chatbot.append((None, f"Doc2x 解析中"))
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
md_zip_path, unzipped_folder = 解析PDF_DOC2X(filepath, format="md")
|
||||
md_zip_path, unzipped_folder = 解析PDF_DOC2X(filepath, format='md')
|
||||
|
||||
promote_file_to_downloadzone(md_zip_path, chatbot=chatbot)
|
||||
chatbot.append((None, f"完成解析 {md_zip_path} ..."))
|
||||
@@ -239,97 +174,77 @@ def 解析PDF_DOC2X_单文件(
|
||||
os.makedirs(target_path_base, exist_ok=True)
|
||||
shutil.copyfile(md_zip_path, this_file_path)
|
||||
ex_folder = this_file_path + ".extract"
|
||||
extract_archive(file_path=this_file_path, dest_dir=ex_folder)
|
||||
extract_archive(
|
||||
file_path=this_file_path, dest_dir=ex_folder
|
||||
)
|
||||
|
||||
# edit markdown files
|
||||
success, file_manifest, project_folder = get_files_from_everything(
|
||||
ex_folder, type=".md"
|
||||
)
|
||||
success, file_manifest, project_folder = get_files_from_everything(ex_folder, type='.md')
|
||||
for generated_fp in file_manifest:
|
||||
# 修正一些公式问题
|
||||
with open(generated_fp, "r", encoding="utf8") as f:
|
||||
with open(generated_fp, 'r', encoding='utf8') as f:
|
||||
content = f.read()
|
||||
# 将公式中的\[ \]替换成$$
|
||||
content = content.replace(r"\[", r"$$").replace(r"\]", r"$$")
|
||||
content = content.replace(r'\[', r'$$').replace(r'\]', r'$$')
|
||||
# 将公式中的\( \)替换成$
|
||||
content = content.replace(r"\(", r"$").replace(r"\)", r"$")
|
||||
content = content.replace("```markdown", "\n").replace("```", "\n")
|
||||
with open(generated_fp, "w", encoding="utf8") as f:
|
||||
content = content.replace(r'\(', r'$').replace(r'\)', r'$')
|
||||
content = content.replace('```markdown', '\n').replace('```', '\n')
|
||||
with open(generated_fp, 'w', encoding='utf8') as f:
|
||||
f.write(content)
|
||||
promote_file_to_downloadzone(generated_fp, chatbot=chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
# 生成在线预览html
|
||||
file_name = "在线预览翻译（原文）" + gen_time_str() + ".html"
|
||||
file_name = '在线预览翻译（原文）' + gen_time_str() + '.html'
|
||||
preview_fp = os.path.join(ex_folder, file_name)
|
||||
from shared_utils.advanced_markdown_format import (
|
||||
markdown_convertion_for_file,
|
||||
)
|
||||
|
||||
from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
||||
with open(generated_fp, "r", encoding="utf-8") as f:
|
||||
md = f.read()
|
||||
# # Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
|
||||
# md = re.sub(r'^<table>', r'.<table>', md, flags=re.MULTILINE)
|
||||
html = markdown_convertion_for_file(md)
|
||||
with open(preview_fp, "w", encoding="utf-8") as f:
|
||||
f.write(html)
|
||||
with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
|
||||
chatbot.append([None, f"生成在线预览：{generate_file_link([preview_fp])}"])
|
||||
promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
|
||||
|
||||
chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
|
||||
plugin_kwargs["markdown_expected_output_dir"] = ex_folder
|
||||
|
||||
translated_f_name = "translated_markdown.md"
|
||||
generated_fp = plugin_kwargs["markdown_expected_output_path"] = os.path.join(
|
||||
ex_folder, translated_f_name
|
||||
)
|
||||
|
||||
chatbot.append((None, f"调用Markdown插件 {ex_folder} ..."))
|
||||
plugin_kwargs['markdown_expected_output_dir'] = ex_folder
|
||||
|
||||
translated_f_name = 'translated_markdown.md'
|
||||
generated_fp = plugin_kwargs['markdown_expected_output_path'] = os.path.join(ex_folder, translated_f_name)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
yield from Markdown英译中(
|
||||
ex_folder,
|
||||
llm_kwargs,
|
||||
plugin_kwargs,
|
||||
chatbot,
|
||||
history,
|
||||
system_prompt,
|
||||
user_request,
|
||||
)
|
||||
yield from Markdown英译中(ex_folder, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
if os.path.exists(generated_fp):
|
||||
# 修正一些公式问题
|
||||
with open(generated_fp, "r", encoding="utf8") as f:
|
||||
content = f.read()
|
||||
content = content.replace("```markdown", "\n").replace("```", "\n")
|
||||
with open(generated_fp, 'r', encoding='utf8') as f: content = f.read()
|
||||
content = content.replace('```markdown', '\n').replace('```', '\n')
|
||||
# Markdown中使用不标准的表格，需要在表格前加上一个emoji，以便公式渲染
|
||||
# content = re.sub(r'^<table>', r'.<table>', content, flags=re.MULTILINE)
|
||||
with open(generated_fp, "w", encoding="utf8") as f:
|
||||
f.write(content)
|
||||
with open(generated_fp, 'w', encoding='utf8') as f: f.write(content)
|
||||
# 生成在线预览html
|
||||
file_name = "在线预览翻译" + gen_time_str() + ".html"
|
||||
file_name = '在线预览翻译' + gen_time_str() + '.html'
|
||||
preview_fp = os.path.join(ex_folder, file_name)
|
||||
from shared_utils.advanced_markdown_format import (
|
||||
markdown_convertion_for_file,
|
||||
)
|
||||
|
||||
from shared_utils.advanced_markdown_format import markdown_convertion_for_file
|
||||
with open(generated_fp, "r", encoding="utf-8") as f:
|
||||
md = f.read()
|
||||
html = markdown_convertion_for_file(md)
|
||||
with open(preview_fp, "w", encoding="utf-8") as f:
|
||||
f.write(html)
|
||||
with open(preview_fp, "w", encoding="utf-8") as f: f.write(html)
|
||||
promote_file_to_downloadzone(preview_fp, chatbot=chatbot)
|
||||
# 生成包含图片的压缩包
|
||||
dest_folder = get_log_folder(chatbot.get_user())
|
||||
zip_name = "翻译后的带图文档.zip"
|
||||
zip_folder(
|
||||
source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name
|
||||
)
|
||||
zip_name = '翻译后的带图文档.zip'
|
||||
zip_folder(source_folder=ex_folder, dest_folder=dest_folder, zip_name=zip_name)
|
||||
zip_fp = os.path.join(dest_folder, zip_name)
|
||||
promote_file_to_downloadzone(zip_fp, chatbot=chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
md_zip_path = yield from pdf2markdown(fp)
|
||||
yield from deliver_to_markdown_plugin(md_zip_path, user_request)
|
||||
|
||||
|
||||
def 解析PDF_基于DOC2X(file_manifest, *args):
|
||||
for index, fp in enumerate(file_manifest):
|
||||
yield from 解析PDF_DOC2X_单文件(fp, *args)
|
||||
return
|
||||
|
||||
|
||||
|
||||
@@ -14,17 +14,17 @@ def extract_text_from_files(txt, chatbot, history):
|
||||
final_result(list):文本内容
|
||||
page_one(list):第一页内容/摘要
|
||||
file_manifest(list):文件路径
|
||||
exception(string):需要用户手动处理的信息,如没出错则保持为空
|
||||
excption(string):需要用户手动处理的信息,如没出错则保持为空
|
||||
"""
|
||||
|
||||
final_result = []
|
||||
page_one = []
|
||||
file_manifest = []
|
||||
exception = ""
|
||||
excption = ""
|
||||
|
||||
if txt == "":
|
||||
final_result.append(txt)
|
||||
return False, final_result, page_one, file_manifest, exception #如输入区内容不是文件则直接返回输入区内容
|
||||
return False, final_result, page_one, file_manifest, excption #如输入区内容不是文件则直接返回输入区内容
|
||||
|
||||
#查找输入区内容中的文件
|
||||
file_pdf,pdf_manifest,folder_pdf = get_files_from_everything(txt, '.pdf')
|
||||
@@ -33,20 +33,20 @@ def extract_text_from_files(txt, chatbot, history):
|
||||
file_doc,doc_manifest,folder_doc = get_files_from_everything(txt, '.doc')
|
||||
|
||||
if file_doc:
|
||||
exception = "word"
|
||||
return False, final_result, page_one, file_manifest, exception
|
||||
excption = "word"
|
||||
return False, final_result, page_one, file_manifest, excption
|
||||
|
||||
file_num = len(pdf_manifest) + len(md_manifest) + len(word_manifest)
|
||||
if file_num == 0:
|
||||
final_result.append(txt)
|
||||
return False, final_result, page_one, file_manifest, exception #如输入区内容不是文件则直接返回输入区内容
|
||||
return False, final_result, page_one, file_manifest, excption #如输入区内容不是文件则直接返回输入区内容
|
||||
|
||||
if file_pdf:
|
||||
try: # 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
import fitz
|
||||
except:
|
||||
exception = "pdf"
|
||||
return False, final_result, page_one, file_manifest, exception
|
||||
excption = "pdf"
|
||||
return False, final_result, page_one, file_manifest, excption
|
||||
for index, fp in enumerate(pdf_manifest):
|
||||
file_content, pdf_one = read_and_clean_pdf_text(fp) # （尝试）按照章节切割PDF
|
||||
file_content = file_content.encode('utf-8', 'ignore').decode() # avoid reading non-utf8 chars
|
||||
@@ -72,8 +72,8 @@ def extract_text_from_files(txt, chatbot, history):
|
||||
try: # 尝试导入依赖，如果缺少依赖，则给出安装建议
|
||||
from docx import Document
|
||||
except:
|
||||
exception = "word_pip"
|
||||
return False, final_result, page_one, file_manifest, exception
|
||||
excption = "word_pip"
|
||||
return False, final_result, page_one, file_manifest, excption
|
||||
for index, fp in enumerate(word_manifest):
|
||||
doc = Document(fp)
|
||||
file_content = '\n'.join([p.text for p in doc.paragraphs])
|
||||
@@ -82,4 +82,4 @@ def extract_text_from_files(txt, chatbot, history):
|
||||
final_result.append(file_content)
|
||||
file_manifest.append(os.path.relpath(fp, folder_word))
|
||||
|
||||
return True, final_result, page_one, file_manifest, exception
|
||||
return True, final_result, page_one, file_manifest, excption
|
||||
@@ -1,13 +1,17 @@
|
||||
import llama_index
|
||||
import os
|
||||
import atexit
|
||||
from loguru import logger
|
||||
from typing import List
|
||||
|
||||
from llama_index.core import Document
|
||||
from llama_index.core.ingestion import run_transformations
|
||||
from llama_index.core.schema import TextNode
|
||||
|
||||
from crazy_functions.rag_fns.vector_store_index import GptacVectorStoreIndex
|
||||
from request_llms.embed_models.openai_embed import OpenAiEmbeddingModel
|
||||
from shared_utils.connect_void_terminal import get_chat_default_kwargs
|
||||
from llama_index.core import VectorStoreIndex, SimpleDirectoryReader
|
||||
from crazy_functions.rag_fns.vector_store_index import GptacVectorStoreIndex
|
||||
from llama_index.core.ingestion import run_transformations
|
||||
from llama_index.core import PromptTemplate
|
||||
from llama_index.core.response_synthesizers import TreeSummarize
|
||||
|
||||
DEFAULT_QUERY_GENERATION_PROMPT = """\
|
||||
Now, you have context information as below:
|
||||
@@ -59,7 +63,7 @@ class SaveLoad():
|
||||
def purge(self):
|
||||
import shutil
|
||||
shutil.rmtree(self.checkpoint_dir, ignore_errors=True)
|
||||
self.vs_index = self.create_new_vs(self.checkpoint_dir)
|
||||
self.vs_index = self.create_new_vs()
|
||||
|
||||
|
||||
class LlamaIndexRagWorker(SaveLoad):
|
||||
@@ -71,7 +75,7 @@ class LlamaIndexRagWorker(SaveLoad):
|
||||
if auto_load_checkpoint:
|
||||
self.vs_index = self.load_from_checkpoint(checkpoint_dir)
|
||||
else:
|
||||
self.vs_index = self.create_new_vs()
|
||||
self.vs_index = self.create_new_vs(checkpoint_dir)
|
||||
atexit.register(lambda: self.save_to_checkpoint(checkpoint_dir))
|
||||
|
||||
def assign_embedding_model(self):
|
||||
@@ -87,21 +91,17 @@ class LlamaIndexRagWorker(SaveLoad):
|
||||
logger.info('oo --------inspect_vector_store end--------')
|
||||
return vector_store_preview
|
||||
|
||||
def add_documents_to_vector_store(self, document_list: List[Document]):
|
||||
"""
|
||||
Adds a list of Document objects to the vector store after processing.
|
||||
"""
|
||||
documents = document_list
|
||||
def add_documents_to_vector_store(self, document_list):
|
||||
documents = [Document(text=t) for t in document_list]
|
||||
documents_nodes = run_transformations(
|
||||
documents, # type: ignore
|
||||
self.vs_index._transformations,
|
||||
show_progress=True
|
||||
)
|
||||
self.vs_index.insert_nodes(documents_nodes)
|
||||
if self.debug_mode:
|
||||
self.inspect_vector_store()
|
||||
if self.debug_mode: self.inspect_vector_store()
|
||||
|
||||
def add_text_to_vector_store(self, text: str):
|
||||
def add_text_to_vector_store(self, text):
|
||||
node = TextNode(text=text)
|
||||
documents_nodes = run_transformations(
|
||||
[node],
|
||||
@@ -109,16 +109,14 @@ class LlamaIndexRagWorker(SaveLoad):
|
||||
show_progress=True
|
||||
)
|
||||
self.vs_index.insert_nodes(documents_nodes)
|
||||
if self.debug_mode:
|
||||
self.inspect_vector_store()
|
||||
if self.debug_mode: self.inspect_vector_store()
|
||||
|
||||
def remember_qa(self, question, answer):
|
||||
formatted_str = QUESTION_ANSWER_RECORD.format(question=question, answer=answer)
|
||||
self.add_text_to_vector_store(formatted_str)
|
||||
|
||||
def retrieve_from_store_with_query(self, query):
|
||||
if self.debug_mode:
|
||||
self.inspect_vector_store()
|
||||
if self.debug_mode: self.inspect_vector_store()
|
||||
retriever = self.vs_index.as_retriever()
|
||||
return retriever.retrieve(query)
|
||||
|
||||
@@ -130,9 +128,3 @@ class LlamaIndexRagWorker(SaveLoad):
|
||||
buf = "\n".join(([f"(No.{i+1} | score {n.score:.3f}): {n.text}" for i, n in enumerate(nodes)]))
|
||||
if self.debug_mode: logger.info(buf)
|
||||
return buf
|
||||
|
||||
def purge_vector_store(self):
|
||||
"""
|
||||
Purges the current vector store and creates a new one.
|
||||
"""
|
||||
self.purge()
|
||||
@@ -1,22 +0,0 @@
|
||||
import os
|
||||
from llama_index.core import SimpleDirectoryReader
|
||||
|
||||
supports_format = ['.csv', '.docx', '.epub', '.ipynb', '.mbox', '.md', '.pdf', '.txt', '.ppt',
|
||||
'.pptm', '.pptx']
|
||||
|
||||
|
||||
# 修改后的 extract_text 函数，结合 SimpleDirectoryReader 和自定义解析逻辑
|
||||
def extract_text(file_path):
|
||||
_, ext = os.path.splitext(file_path.lower())
|
||||
|
||||
# 使用 SimpleDirectoryReader 处理它支持的文件格式
|
||||
if ext in supports_format:
|
||||
try:
|
||||
reader = SimpleDirectoryReader(input_files=[file_path])
|
||||
documents = reader.load_data()
|
||||
if len(documents) > 0:
|
||||
return documents[0].text
|
||||
except Exception as e:
|
||||
pass
|
||||
|
||||
return None
|
||||
@@ -60,7 +60,7 @@ def similarity_search_with_score_by_vector(
|
||||
self, embedding: List[float], k: int = 4
|
||||
) -> List[Tuple[Document, float]]:
|
||||
|
||||
def separate_list(ls: List[int]) -> List[List[int]]:
|
||||
def seperate_list(ls: List[int]) -> List[List[int]]:
|
||||
lists = []
|
||||
ls1 = [ls[0]]
|
||||
for i in range(1, len(ls)):
|
||||
@@ -82,7 +82,7 @@ def similarity_search_with_score_by_vector(
|
||||
continue
|
||||
_id = self.index_to_docstore_id[i]
|
||||
doc = self.docstore.search(_id)
|
||||
if not self.chunk_content:
|
||||
if not self.chunk_conent:
|
||||
if not isinstance(doc, Document):
|
||||
raise ValueError(f"Could not find document for id {_id}, got {doc}")
|
||||
doc.metadata["score"] = int(scores[0][j])
|
||||
@@ -104,12 +104,12 @@ def similarity_search_with_score_by_vector(
|
||||
id_set.add(l)
|
||||
if break_flag:
|
||||
break
|
||||
if not self.chunk_content:
|
||||
if not self.chunk_conent:
|
||||
return docs
|
||||
if len(id_set) == 0 and self.score_threshold > 0:
|
||||
return []
|
||||
id_list = sorted(list(id_set))
|
||||
id_lists = separate_list(id_list)
|
||||
id_lists = seperate_list(id_list)
|
||||
for id_seq in id_lists:
|
||||
for id in id_seq:
|
||||
if id == id_seq[0]:
|
||||
@@ -132,7 +132,7 @@ class LocalDocQA:
|
||||
embeddings: object = None
|
||||
top_k: int = VECTOR_SEARCH_TOP_K
|
||||
chunk_size: int = CHUNK_SIZE
|
||||
chunk_content: bool = True
|
||||
chunk_conent: bool = True
|
||||
score_threshold: int = VECTOR_SEARCH_SCORE_THRESHOLD
|
||||
|
||||
def init_cfg(self,
|
||||
@@ -209,16 +209,16 @@ class LocalDocQA:
|
||||
|
||||
# query 查询内容
|
||||
# vs_path 知识库路径
|
||||
# chunk_content 是否启用上下文关联
|
||||
# chunk_conent 是否启用上下文关联
|
||||
# score_threshold 搜索匹配score阈值
|
||||
# vector_search_top_k 搜索知识库内容条数，默认搜索5条结果
|
||||
# chunk_sizes 匹配单段内容的连接上下文长度
|
||||
def get_knowledge_based_content_test(self, query, vs_path, chunk_content,
|
||||
def get_knowledge_based_conent_test(self, query, vs_path, chunk_conent,
|
||||
score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
|
||||
vector_search_top_k=VECTOR_SEARCH_TOP_K, chunk_size=CHUNK_SIZE,
|
||||
text2vec=None):
|
||||
self.vector_store = FAISS.load_local(vs_path, text2vec)
|
||||
self.vector_store.chunk_content = chunk_content
|
||||
self.vector_store.chunk_conent = chunk_conent
|
||||
self.vector_store.score_threshold = score_threshold
|
||||
self.vector_store.chunk_size = chunk_size
|
||||
|
||||
@@ -241,7 +241,7 @@ class LocalDocQA:
|
||||
|
||||
|
||||
|
||||
def construct_vector_store(vs_id, vs_path, files, sentence_size, history, one_content, one_content_segmentation, text2vec):
|
||||
def construct_vector_store(vs_id, vs_path, files, sentence_size, history, one_conent, one_content_segmentation, text2vec):
|
||||
for file in files:
|
||||
assert os.path.exists(file), "输入文件不存在：" + file
|
||||
import nltk
|
||||
@@ -297,7 +297,7 @@ class knowledge_archive_interface():
|
||||
files=file_manifest,
|
||||
sentence_size=100,
|
||||
history=[],
|
||||
one_content="",
|
||||
one_conent="",
|
||||
one_content_segmentation="",
|
||||
text2vec = self.get_chinese_text2vec(),
|
||||
)
|
||||
@@ -319,19 +319,19 @@ class knowledge_archive_interface():
|
||||
files=[],
|
||||
sentence_size=100,
|
||||
history=[],
|
||||
one_content="",
|
||||
one_conent="",
|
||||
one_content_segmentation="",
|
||||
text2vec = self.get_chinese_text2vec(),
|
||||
)
|
||||
VECTOR_SEARCH_SCORE_THRESHOLD = 0
|
||||
VECTOR_SEARCH_TOP_K = 4
|
||||
CHUNK_SIZE = 512
|
||||
resp, prompt = self.qa_handle.get_knowledge_based_content_test(
|
||||
resp, prompt = self.qa_handle.get_knowledge_based_conent_test(
|
||||
query = txt,
|
||||
vs_path = self.kai_path,
|
||||
score_threshold=VECTOR_SEARCH_SCORE_THRESHOLD,
|
||||
vector_search_top_k=VECTOR_SEARCH_TOP_K,
|
||||
chunk_content=True,
|
||||
chunk_conent=True,
|
||||
chunk_size=CHUNK_SIZE,
|
||||
text2vec = self.get_chinese_text2vec(),
|
||||
)
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import List
|
||||
from toolbox import update_ui_latest_msg, disable_auto_promotion
|
||||
from toolbox import update_ui_lastest_msg, disable_auto_promotion
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
from crazy_functions.json_fns.pydantic_io import GptJsonIO, JsonStringError
|
||||
import copy, json, pickle, os, sys, time
|
||||
@@ -9,14 +9,14 @@ import copy, json, pickle, os, sys, time
|
||||
def read_avail_plugin_enum():
|
||||
from crazy_functional import get_crazy_functions
|
||||
plugin_arr = get_crazy_functions()
|
||||
# remove plugins with out explanation
|
||||
# remove plugins with out explaination
|
||||
plugin_arr = {k:v for k, v in plugin_arr.items() if ('Info' in v) and ('Function' in v)}
|
||||
plugin_arr_info = {"F_{:04d}".format(i):v["Info"] for i, v in enumerate(plugin_arr.values(), start=1)}
|
||||
plugin_arr_dict = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}
|
||||
plugin_arr_dict_parse = {"F_{:04d}".format(i):v for i, v in enumerate(plugin_arr.values(), start=1)}
|
||||
plugin_arr_dict_parse.update({f"F_{i}":v for i, v in enumerate(plugin_arr.values(), start=1)})
|
||||
prompt = json.dumps(plugin_arr_info, ensure_ascii=False, indent=2)
|
||||
prompt = "\n\nThe definition of PluginEnum:\nPluginEnum=" + prompt
|
||||
prompt = "\n\nThe defination of PluginEnum:\nPluginEnum=" + prompt
|
||||
return prompt, plugin_arr_dict, plugin_arr_dict_parse
|
||||
|
||||
def wrap_code(txt):
|
||||
@@ -55,7 +55,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
|
||||
plugin_selection: str = Field(description="The most related plugin from one of the PluginEnum.", default="F_0000")
|
||||
reason_of_selection: str = Field(description="The reason why you should select this plugin.", default="This plugin satisfy user requirement most")
|
||||
# ⭐ ⭐ ⭐ 选择插件
|
||||
yield from update_ui_latest_msg(lastmsg=f"正在执行任务: {txt}\n\n查找可用插件中...", chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(lastmsg=f"正在执行任务: {txt}\n\n查找可用插件中...", chatbot=chatbot, history=history, delay=0)
|
||||
gpt_json_io = GptJsonIO(Plugin)
|
||||
gpt_json_io.format_instructions = "The format of your output should be a json that can be parsed by json.loads.\n"
|
||||
gpt_json_io.format_instructions += """Output example: {"plugin_selection":"F_1234", "reason_of_selection":"F_1234 plugin satisfy user requirement most"}\n"""
|
||||
@@ -74,13 +74,13 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
|
||||
msg += "请求的Prompt为：\n" + wrap_code(get_inputs_show_user(inputs, plugin_arr_enum_prompt))
|
||||
msg += "语言模型回复为：\n" + wrap_code(gpt_reply)
|
||||
msg += "\n但您可以尝试再试一次\n"
|
||||
yield from update_ui_latest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
|
||||
yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
|
||||
return
|
||||
if plugin_sel.plugin_selection not in plugin_arr_dict_parse:
|
||||
msg = f"抱歉, 找不到合适插件执行该任务, 或者{llm_kwargs['llm_model']}无法理解您的需求。"
|
||||
msg += f"语言模型{llm_kwargs['llm_model']}选择了不存在的插件：\n" + wrap_code(gpt_reply)
|
||||
msg += "\n但您可以尝试再试一次\n"
|
||||
yield from update_ui_latest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
|
||||
yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
|
||||
return
|
||||
|
||||
# ⭐ ⭐ ⭐ 确认插件参数
|
||||
@@ -90,7 +90,7 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
|
||||
appendix_info = get_recent_file_prompt_support(chatbot)
|
||||
|
||||
plugin = plugin_arr_dict_parse[plugin_sel.plugin_selection]
|
||||
yield from update_ui_latest_msg(lastmsg=f"正在执行任务: {txt}\n\n提取插件参数...", chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(lastmsg=f"正在执行任务: {txt}\n\n提取插件参数...", chatbot=chatbot, history=history, delay=0)
|
||||
class PluginExplicit(BaseModel):
|
||||
plugin_selection: str = plugin_sel.plugin_selection
|
||||
plugin_arg: str = Field(description="The argument of the plugin.", default="")
|
||||
@@ -109,6 +109,6 @@ def execute_plugin(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prom
|
||||
fn = plugin['Function']
|
||||
fn_name = fn.__name__
|
||||
msg = f'{llm_kwargs["llm_model"]}为您选择了插件: `{fn_name}`\n\n插件说明：{plugin["Info"]}\n\n插件参数：{plugin_sel.plugin_arg}\n\n假如偏离了您的要求，按停止键终止。'
|
||||
yield from update_ui_latest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
|
||||
yield from update_ui_lastest_msg(lastmsg=msg, chatbot=chatbot, history=history, delay=2)
|
||||
yield from fn(plugin_sel.plugin_arg, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, -1)
|
||||
return
|
||||
@@ -1,6 +1,6 @@
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import List
|
||||
from toolbox import update_ui_latest_msg, get_conf
|
||||
from toolbox import update_ui_lastest_msg, get_conf
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
from crazy_functions.json_fns.pydantic_io import GptJsonIO
|
||||
import copy, json, pickle, os, sys
|
||||
@@ -9,7 +9,7 @@ import copy, json, pickle, os, sys
|
||||
def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
|
||||
ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
|
||||
if not ALLOW_RESET_CONFIG:
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
|
||||
chatbot=chatbot, history=history, delay=2
|
||||
)
|
||||
@@ -30,7 +30,7 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
new_option_value: str = Field(description="the new value of the option", default=None)
|
||||
|
||||
# ⭐ ⭐ ⭐ 分析用户意图
|
||||
yield from update_ui_latest_msg(lastmsg=f"正在执行任务: {txt}\n\n读取新配置中", chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(lastmsg=f"正在执行任务: {txt}\n\n读取新配置中", chatbot=chatbot, history=history, delay=0)
|
||||
gpt_json_io = GptJsonIO(ModifyConfigurationIntention)
|
||||
inputs = "Analyze how to change configuration according to following user input, answer me with json: \n\n" + \
|
||||
">> " + txt.rstrip('\n').replace('\n','\n>> ') + '\n\n' + \
|
||||
@@ -44,11 +44,11 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
|
||||
ok = (explicit_conf in txt)
|
||||
if ok:
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}",
|
||||
chatbot=chatbot, history=history, delay=1
|
||||
)
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n新配置{explicit_conf}={user_intention.new_option_value}\n\n正在修改配置中",
|
||||
chatbot=chatbot, history=history, delay=2
|
||||
)
|
||||
@@ -57,25 +57,25 @@ def modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, s
|
||||
from toolbox import set_conf
|
||||
set_conf(explicit_conf, user_intention.new_option_value)
|
||||
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n配置修改完成，重新页面即可生效。", chatbot=chatbot, history=history, delay=1
|
||||
)
|
||||
else:
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"失败，如果需要配置{explicit_conf}，您需要明确说明并在指令中提到它。", chatbot=chatbot, history=history, delay=5
|
||||
)
|
||||
|
||||
def modify_configuration_reboot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention):
|
||||
ALLOW_RESET_CONFIG = get_conf('ALLOW_RESET_CONFIG')
|
||||
if not ALLOW_RESET_CONFIG:
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"当前配置不允许被修改！如需激活本功能，请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件。",
|
||||
chatbot=chatbot, history=history, delay=2
|
||||
)
|
||||
return
|
||||
|
||||
yield from modify_configuration_hot(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_intention)
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n配置修改完成，五秒后即将重启！若出现报错请无视即可。", chatbot=chatbot, history=history, delay=5
|
||||
)
|
||||
os.execl(sys.executable, sys.executable, *sys.argv)
|
||||
|
||||
@@ -5,7 +5,7 @@ class VoidTerminalState():
|
||||
self.reset_state()
|
||||
|
||||
def reset_state(self):
|
||||
self.has_provided_explanation = False
|
||||
self.has_provided_explaination = False
|
||||
|
||||
def lock_plugin(self, chatbot):
|
||||
chatbot._cookies['lock_plugin'] = 'crazy_functions.虚空终端->虚空终端'
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -1,4 +1,4 @@
|
||||
from toolbox import CatchException, update_ui, update_ui_latest_msg
|
||||
from toolbox import CatchException, update_ui, update_ui_lastest_msg
|
||||
from crazy_functions.multi_stage.multi_stage_utils import GptAcademicGameBaseState
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
|
||||
@@ -15,7 +15,7 @@ Testing:
|
||||
|
||||
|
||||
from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, is_the_upload_folder
|
||||
from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_latest_msg
|
||||
from toolbox import promote_file_to_downloadzone, get_log_folder, update_ui_lastest_msg
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
|
||||
from crazy_functions.crazy_utils import input_clipping, try_install_deps
|
||||
from crazy_functions.gen_fns.gen_fns_shared import is_function_successfully_generated
|
||||
@@ -27,7 +27,7 @@ import time
|
||||
import glob
|
||||
import multiprocessing
|
||||
|
||||
template = """
|
||||
templete = """
|
||||
```python
|
||||
import ... # Put dependencies here, e.g. import numpy as np.
|
||||
|
||||
@@ -77,10 +77,10 @@ def gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history):
|
||||
|
||||
# 第二步
|
||||
prompt_compose = [
|
||||
"If previous stage is successful, rewrite the function you have just written to satisfy following template: \n",
|
||||
template
|
||||
"If previous stage is successful, rewrite the function you have just written to satisfy following templete: \n",
|
||||
templete
|
||||
]
|
||||
i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable template. "
|
||||
i_say = "".join(prompt_compose); inputs_show_user = "If previous stage is successful, rewrite the function you have just written to satisfy executable templete. "
|
||||
gpt_say = yield from request_gpt_model_in_new_thread_with_ui_alive(
|
||||
inputs=i_say, inputs_show_user=inputs_show_user,
|
||||
llm_kwargs=llm_kwargs, chatbot=chatbot, history=history,
|
||||
@@ -164,18 +164,18 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
if get_plugin_arg(plugin_kwargs, key="file_path_arg", default=False):
|
||||
file_path = get_plugin_arg(plugin_kwargs, key="file_path_arg", default=None)
|
||||
file_list.append(file_path)
|
||||
yield from update_ui_latest_msg(f"当前文件: {file_path}", chatbot, history, 1)
|
||||
yield from update_ui_lastest_msg(f"当前文件: {file_path}", chatbot, history, 1)
|
||||
elif have_any_recent_upload_files(chatbot):
|
||||
file_dir = get_recent_file_prompt_support(chatbot)
|
||||
file_list = glob.glob(os.path.join(file_dir, '**/*'), recursive=True)
|
||||
yield from update_ui_latest_msg(f"当前文件处理列表: {file_list}", chatbot, history, 1)
|
||||
yield from update_ui_lastest_msg(f"当前文件处理列表: {file_list}", chatbot, history, 1)
|
||||
else:
|
||||
chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
|
||||
yield from update_ui_latest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
|
||||
yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
|
||||
return # 2. 如果没有文件
|
||||
if len(file_list) == 0:
|
||||
chatbot.append(["文件检索", "没有发现任何近期上传的文件。"])
|
||||
yield from update_ui_latest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
|
||||
yield from update_ui_lastest_msg("没有发现任何近期上传的文件。", chatbot, history, 1)
|
||||
return # 2. 如果没有文件
|
||||
|
||||
# 读取文件
|
||||
@@ -183,7 +183,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
|
||||
# 粗心检查
|
||||
if is_the_upload_folder(txt):
|
||||
yield from update_ui_latest_msg(f"请在输入框内填写需求, 然后再次点击该插件! 至于您的文件，不用担心, 文件路径 {txt} 已经被记忆. ", chatbot, history, 1)
|
||||
yield from update_ui_lastest_msg(f"请在输入框内填写需求, 然后再次点击该插件! 至于您的文件，不用担心, 文件路径 {txt} 已经被记忆. ", chatbot, history, 1)
|
||||
return
|
||||
|
||||
# 开始干正事
|
||||
@@ -195,7 +195,7 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
code, installation_advance, txt, file_type, llm_kwargs, chatbot, history = \
|
||||
yield from gpt_interact_multi_step(txt, file_type, llm_kwargs, chatbot, history)
|
||||
chatbot.append(["代码生成阶段结束", ""])
|
||||
yield from update_ui_latest_msg(f"正在验证上述代码的有效性 ...", chatbot, history, 1)
|
||||
yield from update_ui_lastest_msg(f"正在验证上述代码的有效性 ...", chatbot, history, 1)
|
||||
# ⭐ 分离代码块
|
||||
code = get_code_block(code)
|
||||
# ⭐ 检查模块
|
||||
@@ -206,11 +206,11 @@ def 函数动态生成(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_
|
||||
if not traceback: traceback = trimmed_format_exc()
|
||||
# 处理异常
|
||||
if not traceback: traceback = trimmed_format_exc()
|
||||
yield from update_ui_latest_msg(f"第 {j+1}/{MAX_TRY} 次代码生成尝试, 失败了~ 别担心, 我们5秒后再试一次... \n\n此次我们的错误追踪是\n```\n{traceback}\n```\n", chatbot, history, 5)
|
||||
yield from update_ui_lastest_msg(f"第 {j+1}/{MAX_TRY} 次代码生成尝试, 失败了~ 别担心, 我们5秒后再试一次... \n\n此次我们的错误追踪是\n```\n{traceback}\n```\n", chatbot, history, 5)
|
||||
|
||||
# 代码生成结束, 开始执行
|
||||
TIME_LIMIT = 15
|
||||
yield from update_ui_latest_msg(f"开始创建新进程并执行代码! 时间限制 {TIME_LIMIT} 秒. 请等待任务完成... ", chatbot, history, 1)
|
||||
yield from update_ui_lastest_msg(f"开始创建新进程并执行代码! 时间限制 {TIME_LIMIT} 秒. 请等待任务完成... ", chatbot, history, 1)
|
||||
manager = multiprocessing.Manager()
|
||||
return_dict = manager.dict()
|
||||
|
||||
|
||||
@@ -8,7 +8,7 @@
|
||||
|
||||
import time
|
||||
from toolbox import CatchException, update_ui, gen_time_str, trimmed_format_exc, ProxyNetworkActivate
|
||||
from toolbox import get_conf, select_api_key, update_ui_latest_msg, Singleton
|
||||
from toolbox import get_conf, select_api_key, update_ui_lastest_msg, Singleton
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_plugin_arg
|
||||
from crazy_functions.crazy_utils import input_clipping, try_install_deps
|
||||
from crazy_functions.agent_fns.persistent import GradioMultiuserManagerForPersistentClasses
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
from toolbox import CatchException, report_exception, get_log_folder, gen_time_str
|
||||
from toolbox import update_ui, promote_file_to_downloadzone, update_ui_latest_msg, disable_auto_promotion
|
||||
from toolbox import update_ui, promote_file_to_downloadzone, update_ui_lastest_msg, disable_auto_promotion
|
||||
from toolbox import write_history_to_file, promote_file_to_downloadzone
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from crazy_functions.crazy_utils import request_gpt_model_multi_threads_with_very_awesome_ui_and_high_efficiency
|
||||
|
||||
@@ -166,7 +166,7 @@ class PointWithTrace(Scene):
|
||||
|
||||
```
|
||||
|
||||
# do not use get_graph, this function is deprecated
|
||||
# do not use get_graph, this funciton is deprecated
|
||||
|
||||
class ExampleFunctionGraph(Scene):
|
||||
def construct(self):
|
||||
|
||||
@@ -324,16 +324,16 @@ def 生成多种Mermaid图表(
|
||||
if os.path.exists(txt): # 如输入区无内容则直接解析历史记录
|
||||
from crazy_functions.pdf_fns.parse_word import extract_text_from_files
|
||||
|
||||
file_exist, final_result, page_one, file_manifest, exception = (
|
||||
file_exist, final_result, page_one, file_manifest, excption = (
|
||||
extract_text_from_files(txt, chatbot, history)
|
||||
)
|
||||
else:
|
||||
file_exist = False
|
||||
exception = ""
|
||||
excption = ""
|
||||
file_manifest = []
|
||||
|
||||
if exception != "":
|
||||
if exception == "word":
|
||||
if excption != "":
|
||||
if excption == "word":
|
||||
report_exception(
|
||||
chatbot,
|
||||
history,
|
||||
@@ -341,7 +341,7 @@ def 生成多种Mermaid图表(
|
||||
b=f"找到了.doc文件，但是该文件格式不被支持，请先转化为.docx格式。",
|
||||
)
|
||||
|
||||
elif exception == "pdf":
|
||||
elif excption == "pdf":
|
||||
report_exception(
|
||||
chatbot,
|
||||
history,
|
||||
@@ -349,7 +349,7 @@ def 生成多种Mermaid图表(
|
||||
b=f"导入软件依赖失败。使用该模块需要额外依赖，安装方法```pip install --upgrade pymupdf```。",
|
||||
)
|
||||
|
||||
elif exception == "word_pip":
|
||||
elif excption == "word_pip":
|
||||
report_exception(
|
||||
chatbot,
|
||||
history,
|
||||
|
||||
@@ -1,4 +1,4 @@
|
||||
from toolbox import CatchException, update_ui, ProxyNetworkActivate, update_ui_latest_msg, get_log_folder, get_user
|
||||
from toolbox import CatchException, update_ui, ProxyNetworkActivate, update_ui_lastest_msg, get_log_folder, get_user
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive, get_files_from_everything
|
||||
from loguru import logger
|
||||
install_msg ="""
|
||||
@@ -42,7 +42,7 @@ def 知识库文件注入(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
# from crazy_functions.crazy_utils import try_install_deps
|
||||
# try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
|
||||
# yield from update_ui_latest_msg("安装完成，您可以再次重试。", chatbot, history)
|
||||
# yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
|
||||
return
|
||||
|
||||
# < --------------------读取文件--------------- >
|
||||
@@ -95,7 +95,7 @@ def 读取知识库作答(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
# from crazy_functions.crazy_utils import try_install_deps
|
||||
# try_install_deps(['zh_langchain==0.2.1', 'pypinyin'], reload_m=['pypinyin', 'zh_langchain'])
|
||||
# yield from update_ui_latest_msg("安装完成，您可以再次重试。", chatbot, history)
|
||||
# yield from update_ui_lastest_msg("安装完成，您可以再次重试。", chatbot, history)
|
||||
return
|
||||
|
||||
# < ------------------- --------------- >
|
||||
|
||||
@@ -47,7 +47,7 @@ explain_msg = """
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import List
|
||||
from toolbox import CatchException, update_ui, is_the_upload_folder
|
||||
from toolbox import update_ui_latest_msg, disable_auto_promotion
|
||||
from toolbox import update_ui_lastest_msg, disable_auto_promotion
|
||||
from request_llms.bridge_all import predict_no_ui_long_connection
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from crazy_functions.crazy_utils import input_clipping
|
||||
@@ -113,19 +113,19 @@ def 虚空终端(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt
|
||||
# 用简单的关键词检测用户意图
|
||||
is_certain, _ = analyze_intention_with_simple_rules(txt)
|
||||
if is_the_upload_folder(txt):
|
||||
state.set_state(chatbot=chatbot, key='has_provided_explanation', value=False)
|
||||
state.set_state(chatbot=chatbot, key='has_provided_explaination', value=False)
|
||||
appendix_msg = "\n\n**很好，您已经上传了文件**，现在请您描述您的需求。"
|
||||
|
||||
if is_certain or (state.has_provided_explanation):
|
||||
if is_certain or (state.has_provided_explaination):
|
||||
# 如果意图明确，跳过提示环节
|
||||
state.set_state(chatbot=chatbot, key='has_provided_explanation', value=True)
|
||||
state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True)
|
||||
state.unlock_plugin(chatbot=chatbot)
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
yield from 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, system_prompt, user_request)
|
||||
return
|
||||
else:
|
||||
# 如果意图模糊，提示
|
||||
state.set_state(chatbot=chatbot, key='has_provided_explanation', value=True)
|
||||
state.set_state(chatbot=chatbot, key='has_provided_explaination', value=True)
|
||||
state.lock_plugin(chatbot=chatbot)
|
||||
chatbot.append(("虚空终端状态:", explain_msg+appendix_msg))
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
@@ -141,7 +141,7 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
# ⭐ ⭐ ⭐ 分析用户意图
|
||||
is_certain, user_intention = analyze_intention_with_simple_rules(txt)
|
||||
if not is_certain:
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n分析用户意图中", chatbot=chatbot, history=history, delay=0)
|
||||
gpt_json_io = GptJsonIO(UserIntention)
|
||||
rf_req = "\nchoose from ['ModifyConfiguration', 'ExecutePlugin', 'Chat']"
|
||||
@@ -154,13 +154,13 @@ def 虚空终端主路由(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
user_intention = gpt_json_io.generate_output_auto_repair(analyze_res, run_gpt_fn)
|
||||
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
|
||||
except JsonStringError as e:
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 失败 当前语言模型（{llm_kwargs['llm_model']}）不能理解您的意图", chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
else:
|
||||
pass
|
||||
|
||||
yield from update_ui_latest_msg(
|
||||
yield from update_ui_lastest_msg(
|
||||
lastmsg=f"正在执行任务: {txt}\n\n用户意图理解: 意图={explain_intention_to_user[user_intention.intention_type]}",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
|
||||
|
||||
@@ -42,7 +42,7 @@ class AsyncGptTask():
|
||||
MAX_TOKEN_ALLO = 2560
|
||||
i_say, history = input_clipping(i_say, history, max_token_limit=MAX_TOKEN_ALLO)
|
||||
gpt_say_partial = predict_no_ui_long_connection(inputs=i_say, llm_kwargs=llm_kwargs, history=history, sys_prompt=sys_prompt,
|
||||
observe_window=observe_window[index], console_silence=True)
|
||||
observe_window=observe_window[index], console_slience=True)
|
||||
except ConnectionAbortedError as token_exceed_err:
|
||||
logger.error('至少一个线程任务Token溢出而失败', e)
|
||||
except Exception as e:
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
from crazy_functions.crazy_utils import request_gpt_model_in_new_thread_with_ui_alive
|
||||
from toolbox import CatchException, report_exception, promote_file_to_downloadzone
|
||||
from toolbox import update_ui, update_ui_latest_msg, disable_auto_promotion, write_history_to_file
|
||||
from toolbox import update_ui, update_ui_lastest_msg, disable_auto_promotion, write_history_to_file
|
||||
import logging
|
||||
import requests
|
||||
import time
|
||||
@@ -156,7 +156,7 @@ def 谷歌检索小助手(txt, llm_kwargs, plugin_kwargs, chatbot, history, syst
|
||||
history = []
|
||||
meta_paper_info_list = yield from get_meta_information(txt, chatbot, history)
|
||||
if len(meta_paper_info_list) == 0:
|
||||
yield from update_ui_latest_msg(lastmsg='获取文献失败，可能触发了google反爬虫机制。',chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(lastmsg='获取文献失败，可能触发了google反爬虫机制。',chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
batchsize = 5
|
||||
for batch in range(math.ceil(len(meta_paper_info_list)/batchsize)):
|
||||
|
||||
@@ -5,10 +5,6 @@ FROM fuqingxu/11.3.1-runtime-ubuntu20.04-with-texlive:latest
|
||||
|
||||
# edge-tts需要的依赖，某些pip包所需的依赖
|
||||
RUN apt update && apt install ffmpeg build-essential -y
|
||||
RUN apt-get install -y fontconfig
|
||||
RUN ln -s /usr/local/texlive/2023/texmf-dist/fonts/truetype /usr/share/fonts/truetype/texlive
|
||||
RUN fc-cache -fv
|
||||
RUN apt-get clean
|
||||
|
||||
# use python3 as the system default python
|
||||
WORKDIR /gpt
|
||||
@@ -34,7 +30,7 @@ RUN python3 -m pip install -r request_llms/requirements_qwen.txt
|
||||
RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
|
||||
RUN python3 -m pip install -r request_llms/requirements_newbing.txt
|
||||
RUN python3 -m pip install nougat-ocr
|
||||
RUN python3 -m pip cache purge
|
||||
|
||||
|
||||
# 预热Tiktoken模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
@@ -7,7 +7,6 @@ RUN apt-get install -y git python python3 python-dev python3-dev --fix-missing
|
||||
|
||||
# edge-tts需要的依赖，某些pip包所需的依赖
|
||||
RUN apt update && apt install ffmpeg build-essential -y
|
||||
RUN apt-get clean
|
||||
|
||||
# use python3 as the system default python
|
||||
RUN curl -sS https://bootstrap.pypa.io/get-pip.py | python3.8
|
||||
@@ -23,7 +22,6 @@ RUN python3 -m pip install -r request_llms/requirements_moss.txt
|
||||
RUN python3 -m pip install -r request_llms/requirements_qwen.txt
|
||||
RUN python3 -m pip install -r request_llms/requirements_chatglm.txt
|
||||
RUN python3 -m pip install -r request_llms/requirements_newbing.txt
|
||||
RUN python3 -m pip cache purge
|
||||
|
||||
|
||||
# 预热Tiktoken模块
|
||||
|
||||
@@ -18,7 +18,5 @@ RUN apt update && apt install ffmpeg -y
|
||||
# 可选步骤，用于预热模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
RUN python3 -m pip cache purge && apt-get clean
|
||||
|
||||
# 启动
|
||||
CMD ["python3", "-u", "main.py"]
|
||||
|
||||
@@ -30,7 +30,5 @@ COPY --chown=gptuser:gptuser . .
|
||||
# 可选步骤，用于预热模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
|
||||
RUN python3 -m pip cache purge
|
||||
|
||||
# 启动
|
||||
CMD ["python3", "-u", "main.py"]
|
||||
|
||||
@@ -24,8 +24,6 @@ RUN apt update && apt install ffmpeg -y
|
||||
|
||||
# 可选步骤，用于预热模块
|
||||
RUN python3 -c 'from check_proxy import warm_up_modules; warm_up_modules()'
|
||||
RUN python3 -m pip cache purge && apt-get clean
|
||||
|
||||
|
||||
# 启动
|
||||
CMD ["python3", "-u", "main.py"]
|
||||
|
||||
@@ -1,26 +0,0 @@
|
||||
@echo off
|
||||
setlocal
|
||||
|
||||
:: 设置环境变量
|
||||
set ENV_NAME=gpt
|
||||
set ENV_PATH=%~dp0%ENV_NAME%
|
||||
set SCRIPT_PATH=%~dp0main.py
|
||||
|
||||
:: 判断环境是否已解压
|
||||
if not exist "%ENV_PATH%" (
|
||||
echo Extracting environment...
|
||||
mkdir "%ENV_PATH%"
|
||||
tar -xzf gpt.tar.gz -C "%ENV_PATH%"
|
||||
|
||||
:: 运行conda环境激活脚本
|
||||
call "%ENV_PATH%\Scripts\activate.bat"
|
||||
) else (
|
||||
:: 如果环境已存在,直接激活
|
||||
call "%ENV_PATH%\Scripts\activate.bat"
|
||||
)
|
||||
echo Start to run program:
|
||||
:: 运行Python脚本
|
||||
python "%SCRIPT_PATH%"
|
||||
|
||||
endlocal
|
||||
pause
|
||||
@@ -149,6 +149,19 @@
|
||||
DEFINE_ARG_INPUT_INTERFACE = json.dumps(define_arg_selection)
|
||||
return base64.b64encode(DEFINE_ARG_INPUT_INTERFACE.encode('utf-8')).decode('utf-8')
|
||||
```
|
||||
1-2. 预留4个动态插件按钮（常规状态隐藏）
|
||||
|
||||
点击 “+插件按钮”：跳转到插件市场
|
||||
|
||||
点击 加载插件：
|
||||
- 下载文件
|
||||
- 注册 exe_dynamic_plugin开始执行
|
||||
- 执行浏览器js函数
|
||||
|
||||
点击动态插件按钮
|
||||
- js： 检查register_advanced_plugin_init_code_arr，如果为空，提示
|
||||
- 如果非空，先跳二级菜单，设定诸元后，执行一个隐藏的按钮 -- 关联 exe_dynamic_plugin
|
||||
- exe_dynamic_plugin开始执行
|
||||
|
||||
|
||||
2. 用户加载阶段（主javascript程序`common.js`中），浏览器加载`register_advanced_plugin_init_code_arr`，存入本地的字典`advanced_plugin_init_code_lib`：
|
||||
|
||||
@@ -1141,7 +1141,7 @@
|
||||
"内容太长了都会触发token数量溢出的错误": "An error of token overflow will be triggered if the content is too long",
|
||||
"chatbot 为WebUI中显示的对话列表": "chatbot is the conversation list displayed in WebUI",
|
||||
"修改它": "Modify it",
|
||||
"然后yield出去": "Then yield it out",
|
||||
"然后yeild出去": "Then yield it out",
|
||||
"可以直接修改对话界面内容": "You can directly modify the conversation interface content",
|
||||
"additional_fn代表点击的哪个按钮": "additional_fn represents which button is clicked",
|
||||
"按钮见functional.py": "See functional.py for buttons",
|
||||
@@ -1732,7 +1732,7 @@
|
||||
"或者重启之后再度尝试": "Or try again after restarting",
|
||||
"免费": "Free",
|
||||
"仅在Windows系统进行了测试": "Tested only on Windows system",
|
||||
"欢迎加README中的QQ联系开发者": "Feel free to contact the developer via QQ in README",
|
||||
"欢迎加REAME中的QQ联系开发者": "Feel free to contact the developer via QQ in REAME",
|
||||
"当前知识库内的有效文件": "Valid files in the current knowledge base",
|
||||
"您可以到Github Issue区": "You can go to the Github Issue area",
|
||||
"刷新Gradio前端界面": "Refresh the Gradio frontend interface",
|
||||
@@ -1759,7 +1759,7 @@
|
||||
"报错信息如下. 如果是与网络相关的问题": "Error message as follows. If it is related to network issues",
|
||||
"功能描述": "Function description",
|
||||
"禁止移除或修改此警告": "Removal or modification of this warning is prohibited",
|
||||
"ArXiv翻译": "ArXiv translation",
|
||||
"Arixv翻译": "Arixv translation",
|
||||
"读取优先级": "Read priority",
|
||||
"包含documentclass关键字": "Contains the documentclass keyword",
|
||||
"根据文本使用GPT模型生成相应的图像": "Generate corresponding images using GPT model based on the text",
|
||||
@@ -1998,7 +1998,7 @@
|
||||
"开始最终总结": "Start final summary",
|
||||
"openai的官方KEY需要伴随组织编码": "Openai's official KEY needs to be accompanied by organizational code",
|
||||
"将子线程的gpt结果写入chatbot": "Write the GPT result of the sub-thread into the chatbot",
|
||||
"ArXiv论文精细翻译": "Fine translation of ArXiv paper",
|
||||
"Arixv论文精细翻译": "Fine translation of Arixv paper",
|
||||
"开始接收chatglmft的回复": "Start receiving replies from chatglmft",
|
||||
"请先将.doc文档转换为.docx文档": "Please convert .doc documents to .docx documents first",
|
||||
"避免多用户干扰": "Avoid multiple user interference",
|
||||
@@ -2360,7 +2360,7 @@
|
||||
"请在config.py中设置ALLOW_RESET_CONFIG=True后重启软件": "Please set ALLOW_RESET_CONFIG=True in config.py and restart the software",
|
||||
"按照自然语言描述生成一个动画 | 输入参数是一段话": "Generate an animation based on natural language description | Input parameter is a sentence",
|
||||
"你的hf用户名如qingxu98": "Your hf username is qingxu98",
|
||||
"ArXiv论文精细翻译 | 输入参数arxiv论文的ID": "Fine translation of ArXiv paper | Input parameter is the ID of arxiv paper",
|
||||
"Arixv论文精细翻译 | 输入参数arxiv论文的ID": "Fine translation of Arixv paper | Input parameter is the ID of arxiv paper",
|
||||
"无法获取 abstract": "Unable to retrieve abstract",
|
||||
"尽可能地仅用一行命令解决我的要求": "Try to solve my request using only one command",
|
||||
"提取插件参数": "Extract plugin parameters",
|
||||
|
||||
@@ -753,7 +753,7 @@
|
||||
"手动指定和筛选源代码文件类型": "ソースコードファイルタイプを手動で指定およびフィルタリングする",
|
||||
"更多函数插件": "その他の関数プラグイン",
|
||||
"看门狗的耐心": "監視犬の忍耐力",
|
||||
"然后yield出去": "そして出力する",
|
||||
"然后yeild出去": "そして出力する",
|
||||
"拆分过长的IPynb文件": "長すぎるIPynbファイルを分割する",
|
||||
"1. 把input的余量留出来": "1. 入力の余裕を残す",
|
||||
"请求超时": "リクエストがタイムアウトしました",
|
||||
@@ -1803,7 +1803,7 @@
|
||||
"默认值为1000": "デフォルト値は1000です",
|
||||
"写出文件": "ファイルに書き出す",
|
||||
"生成的视频文件路径": "生成されたビデオファイルのパス",
|
||||
"ArXiv论文精细翻译": "ArXiv論文の詳細な翻訳",
|
||||
"Arixv论文精细翻译": "Arixv論文の詳細な翻訳",
|
||||
"用latex编译为PDF对修正处做高亮": "LaTeXでコンパイルしてPDFに修正をハイライトする",
|
||||
"点击“停止”键可终止程序": "「停止」ボタンをクリックしてプログラムを終了できます",
|
||||
"否则将导致每个人的Claude问询历史互相渗透": "さもないと、各人のClaudeの問い合わせ履歴が相互に侵入します",
|
||||
@@ -1987,7 +1987,7 @@
|
||||
"前面是中文逗号": "前面是中文逗号",
|
||||
"的依赖": "的依赖",
|
||||
"材料如下": "材料如下",
|
||||
"欢迎加README中的QQ联系开发者": "欢迎加README中的QQ联系开发者",
|
||||
"欢迎加REAME中的QQ联系开发者": "欢迎加REAME中的QQ联系开发者",
|
||||
"开始下载": "開始ダウンロード",
|
||||
"100字以内": "100文字以内",
|
||||
"创建request": "リクエストの作成",
|
||||
|
||||
@@ -771,7 +771,7 @@
|
||||
"查询代理的地理位置": "查詢代理的地理位置",
|
||||
"是否在输入过长时": "是否在輸入過長時",
|
||||
"chatGPT分析报告": "chatGPT分析報告",
|
||||
"然后yield出去": "然後yield出去",
|
||||
"然后yeild出去": "然後yield出去",
|
||||
"用户取消了程序": "使用者取消了程式",
|
||||
"琥珀色": "琥珀色",
|
||||
"这里是特殊函数插件的高级参数输入区": "這裡是特殊函數插件的高級參數輸入區",
|
||||
@@ -1587,7 +1587,7 @@
|
||||
"否则将导致每个人的Claude问询历史互相渗透": "否則將導致每個人的Claude問詢歷史互相滲透",
|
||||
"提问吧! 但注意": "提問吧！但注意",
|
||||
"待处理的word文档路径": "待處理的word文檔路徑",
|
||||
"欢迎加README中的QQ联系开发者": "歡迎加README中的QQ聯繫開發者",
|
||||
"欢迎加REAME中的QQ联系开发者": "歡迎加REAME中的QQ聯繫開發者",
|
||||
"建议暂时不要使用": "建議暫時不要使用",
|
||||
"Latex没有安装": "Latex沒有安裝",
|
||||
"在这里放一些网上搜集的demo": "在這裡放一些網上搜集的demo",
|
||||
@@ -1989,7 +1989,7 @@
|
||||
"请耐心等待": "請耐心等待",
|
||||
"在执行完成之后": "在執行完成之後",
|
||||
"参数简单": "參數簡單",
|
||||
"ArXiv论文精细翻译": "ArXiv論文精細翻譯",
|
||||
"Arixv论文精细翻译": "Arixv論文精細翻譯",
|
||||
"备份和下载": "備份和下載",
|
||||
"当前报错的latex代码处于第": "當前報錯的latex代碼處於第",
|
||||
"Markdown翻译": "Markdown翻譯",
|
||||
|
||||
43
main.py
43
main.py
@@ -1,7 +1,10 @@
|
||||
import os; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
|
||||
import os, json; os.environ['no_proxy'] = '*' # 避免代理网络产生意外污染
|
||||
|
||||
help_menu_description = \
|
||||
"""
|
||||
"""Github源代码开源和更新[地址🚀](https://github.com/binary-husky/gpt_academic),
|
||||
感谢热情的[开发者们❤️](https://github.com/binary-husky/gpt_academic/graphs/contributors).
|
||||
</br></br>常见问题请查阅[项目Wiki](https://github.com/binary-husky/gpt_academic/wiki),
|
||||
如遇到Bug请前往[Bug反馈](https://github.com/binary-husky/gpt_academic/issues).
|
||||
</br></br>普通对话使用说明: 1. 输入问题; 2. 点击提交
|
||||
</br></br>基础功能区使用说明: 1. 输入文本; 2. 点击任意基础功能区按钮
|
||||
</br></br>函数插件区使用说明: 1. 输入路径/问题, 或者上传文件; 2. 点击任意函数插件区按钮
|
||||
@@ -31,7 +34,7 @@ def encode_plugin_info(k, plugin)->str:
|
||||
|
||||
def main():
|
||||
import gradio as gr
|
||||
if gr.__version__ not in ['3.32.12']:
|
||||
if gr.__version__ not in ['3.32.9', '3.32.10', '3.32.11']:
|
||||
raise ModuleNotFoundError("使用项目内置Gradio获取最优体验! 请运行 `pip install -r requirements.txt` 指令安装内置Gradio及其他依赖, 详情信息见requirements.txt.")
|
||||
|
||||
# 一些基础工具
|
||||
@@ -46,7 +49,7 @@ def main():
|
||||
# 读取配置
|
||||
proxies, WEB_PORT, LLM_MODEL, CONCURRENT_COUNT, AUTHENTICATION = get_conf('proxies', 'WEB_PORT', 'LLM_MODEL', 'CONCURRENT_COUNT', 'AUTHENTICATION')
|
||||
CHATBOT_HEIGHT, LAYOUT, AVAIL_LLM_MODELS, AUTO_CLEAR_TXT = get_conf('CHATBOT_HEIGHT', 'LAYOUT', 'AVAIL_LLM_MODELS', 'AUTO_CLEAR_TXT')
|
||||
ENABLE_AUDIO, AUTO_CLEAR_TXT, AVAIL_FONTS, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'AVAIL_FONTS', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
|
||||
ENABLE_AUDIO, AUTO_CLEAR_TXT, PATH_LOGGING, AVAIL_THEMES, THEME, ADD_WAIFU = get_conf('ENABLE_AUDIO', 'AUTO_CLEAR_TXT', 'PATH_LOGGING', 'AVAIL_THEMES', 'THEME', 'ADD_WAIFU')
|
||||
NUM_CUSTOM_BASIC_BTN, SSL_KEYFILE, SSL_CERTFILE = get_conf('NUM_CUSTOM_BASIC_BTN', 'SSL_KEYFILE', 'SSL_CERTFILE')
|
||||
DARK_MODE, INIT_SYS_PROMPT, ADD_WAIFU, TTS_TYPE = get_conf('DARK_MODE', 'INIT_SYS_PROMPT', 'ADD_WAIFU', 'TTS_TYPE')
|
||||
if LLM_MODEL not in AVAIL_LLM_MODELS: AVAIL_LLM_MODELS += [LLM_MODEL]
|
||||
@@ -54,8 +57,8 @@ def main():
|
||||
# 如果WEB_PORT是-1, 则随机选取WEB端口
|
||||
PORT = find_free_port() if WEB_PORT <= 0 else WEB_PORT
|
||||
from check_proxy import get_current_version
|
||||
from themes.theme import adjust_theme, advanced_css, theme_declaration, js_code_clear, js_code_show_or_hide
|
||||
from themes.theme import js_code_for_toggle_darkmode
|
||||
from themes.theme import adjust_theme, advanced_css, theme_declaration, js_code_clear, js_code_reset, js_code_show_or_hide, js_code_show_or_hide_group2
|
||||
from themes.theme import js_code_for_toggle_darkmode, js_code_for_persistent_cookie_init
|
||||
from themes.theme import load_dynamic_theme, to_cookie_str, from_cookie_str, assign_user_uuid
|
||||
title_html = f"<h1 align=\"center\">GPT 学术优化 {get_current_version()}</h1>{theme_declaration}"
|
||||
|
||||
@@ -65,7 +68,7 @@ def main():
|
||||
functional = get_core_functions()
|
||||
|
||||
# 高级函数插件
|
||||
from crazy_functional import get_crazy_functions, get_multiplex_button_functions
|
||||
from crazy_functional import get_crazy_functions
|
||||
DEFAULT_FN_GROUPS = get_conf('DEFAULT_FN_GROUPS')
|
||||
plugins = get_crazy_functions()
|
||||
all_plugin_groups = list(set([g for _, plugin in plugins.items() for g in plugin['Group'].split('|')]))
|
||||
@@ -103,7 +106,7 @@ def main():
|
||||
with gr_L2(scale=2, elem_id="gpt-chat"):
|
||||
chatbot = gr.Chatbot(label=f"当前模型：{LLM_MODEL}", elem_id="gpt-chatbot")
|
||||
if LAYOUT == "TOP-DOWN": chatbot.style(height=CHATBOT_HEIGHT)
|
||||
history, _, _ = make_history_cache() # 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
|
||||
history, history_cache, history_cache_update = make_history_cache() # 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
|
||||
with gr_L2(scale=1, elem_id="gpt-panel"):
|
||||
with gr.Accordion("输入区", open=True, elem_id="input-panel") as area_input_primary:
|
||||
with gr.Row():
|
||||
@@ -111,7 +114,12 @@ def main():
|
||||
with gr.Row(elem_id="gpt-submit-row"):
|
||||
multiplex_submit_btn = gr.Button("提交", elem_id="elem_submit_visible", variant="primary")
|
||||
multiplex_sel = gr.Dropdown(
|
||||
choices=get_multiplex_button_functions().keys(), value="常规对话",
|
||||
choices=[
|
||||
"常规对话",
|
||||
"多模型对话",
|
||||
"智能召回 RAG",
|
||||
# "智能上下文",
|
||||
], value="常规对话",
|
||||
interactive=True, label='', show_label=False,
|
||||
elem_classes='normal_mut_select', elem_id="gpt-submit-dropdown").style(container=False)
|
||||
submit_btn = gr.Button("提交", elem_id="elem_submit", variant="primary", visible=False)
|
||||
@@ -171,20 +179,16 @@ def main():
|
||||
with gr.Accordion("点击展开“文件下载区”。", open=False) as area_file_up:
|
||||
file_upload = gr.Files(label="任何文件, 推荐上传压缩文件(zip, tar)", file_count="multiple", elem_id="elem_upload")
|
||||
|
||||
|
||||
# 左上角工具栏定义
|
||||
from themes.gui_toolbar import define_gui_toolbar
|
||||
checkboxes, checkboxes_2, max_length_sl, theme_dropdown, system_prompt, file_upload_2, md_dropdown, top_p, temperature = \
|
||||
define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, AVAIL_FONTS, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode)
|
||||
define_gui_toolbar(AVAIL_LLM_MODELS, LLM_MODEL, INIT_SYS_PROMPT, THEME, AVAIL_THEMES, ADD_WAIFU, help_menu_description, js_code_for_toggle_darkmode)
|
||||
|
||||
# 浮动菜单定义
|
||||
from themes.gui_floating_menu import define_gui_floating_menu
|
||||
area_input_secondary, txt2, area_customize, _, resetBtn2, clearBtn2, stopBtn2 = \
|
||||
define_gui_floating_menu(customize_btns, functional, predefined_btns, cookies, web_cookie_cache)
|
||||
|
||||
# 浮动时间线定义
|
||||
gr.Spark()
|
||||
|
||||
# 插件二级菜单的实现
|
||||
from themes.gui_advanced_plugin_class import define_gui_advanced_plugin_class
|
||||
new_plugin_callback, route_switchy_bt_with_arg, usr_confirmed_arg = \
|
||||
@@ -207,7 +211,7 @@ def main():
|
||||
ret.update({area_customize: gr.update(visible=("自定义菜单" in a))})
|
||||
return ret
|
||||
checkboxes_2.select(fn_area_visibility_2, [checkboxes_2], [area_customize] )
|
||||
checkboxes_2.select(None, [checkboxes_2], None, _js="""apply_checkbox_change_for_group2""")
|
||||
checkboxes_2.select(None, [checkboxes_2], None, _js=js_code_show_or_hide_group2)
|
||||
|
||||
# 整理反复出现的控件句柄组合
|
||||
input_combo = [cookies, max_length_sl, md_dropdown, txt, txt2, top_p, temperature, chatbot, history, system_prompt, plugin_advanced_arg]
|
||||
@@ -223,8 +227,11 @@ def main():
|
||||
multiplex_sel.select(
|
||||
None, [multiplex_sel], None, _js=f"""(multiplex_sel)=>run_multiplex_shift(multiplex_sel)""")
|
||||
cancel_handles.append(submit_btn.click(**predict_args))
|
||||
resetBtn.click(None, None, [chatbot, history, status], _js= """clear_conversation""") # 先在前端快速清除chatbot&status
|
||||
resetBtn2.click(None, None, [chatbot, history, status], _js="""clear_conversation""") # 先在前端快速清除chatbot&status
|
||||
resetBtn.click(None, None, [chatbot, history, status], _js=js_code_reset) # 先在前端快速清除chatbot&status
|
||||
resetBtn2.click(None, None, [chatbot, history, status], _js=js_code_reset) # 先在前端快速清除chatbot&status
|
||||
reset_server_side_args = (lambda history: ([], [], "已重置", json.dumps(history)), [history], [chatbot, history, status, history_cache])
|
||||
resetBtn.click(*reset_server_side_args) # 再在后端清除history，把history转存history_cache备用
|
||||
resetBtn2.click(*reset_server_side_args) # 再在后端清除history，把history转存history_cache备用
|
||||
clearBtn.click(None, None, [txt, txt2], _js=js_code_clear)
|
||||
clearBtn2.click(None, None, [txt, txt2], _js=js_code_clear)
|
||||
if AUTO_CLEAR_TXT:
|
||||
@@ -324,7 +331,7 @@ def main():
|
||||
from shared_utils.cookie_manager import load_web_cookie_cache__fn_builder
|
||||
load_web_cookie_cache = load_web_cookie_cache__fn_builder(customize_btns, cookies, predefined_btns)
|
||||
app_block.load(load_web_cookie_cache, inputs = [web_cookie_cache, cookies],
|
||||
outputs = [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()], _js="""persistent_cookie_init""")
|
||||
outputs = [web_cookie_cache, cookies, *customize_btns.values(), *predefined_btns.values()], _js=js_code_for_persistent_cookie_init)
|
||||
app_block.load(None, inputs=[], outputs=None, _js=f"""()=>GptAcademicJavaScriptInit("{DARK_MODE}","{INIT_SYS_PROMPT}","{ADD_WAIFU}","{LAYOUT}","{TTS_TYPE}")""") # 配置暗色主题或亮色主题
|
||||
app_block.load(None, inputs=[], outputs=None, _js="""()=>{REP}""".replace("REP", register_advanced_plugin_init_arr))
|
||||
|
||||
|
||||
@@ -26,9 +26,6 @@ from .bridge_chatglm import predict as chatglm_ui
|
||||
from .bridge_chatglm3 import predict_no_ui_long_connection as chatglm3_noui
|
||||
from .bridge_chatglm3 import predict as chatglm3_ui
|
||||
|
||||
from .bridge_chatglm4 import predict_no_ui_long_connection as chatglm4_noui
|
||||
from .bridge_chatglm4 import predict as chatglm4_ui
|
||||
|
||||
from .bridge_qianfan import predict_no_ui_long_connection as qianfan_noui
|
||||
from .bridge_qianfan import predict as qianfan_ui
|
||||
|
||||
@@ -79,7 +76,6 @@ cohere_endpoint = "https://api.cohere.ai/v1/chat"
|
||||
ollama_endpoint = "http://localhost:11434/api/chat"
|
||||
yimodel_endpoint = "https://api.lingyiwanwu.com/v1/chat/completions"
|
||||
deepseekapi_endpoint = "https://api.deepseek.com/v1/chat/completions"
|
||||
grok_model_endpoint = "https://api.x.ai/v1/chat/completions"
|
||||
|
||||
if not AZURE_ENDPOINT.endswith('/'): AZURE_ENDPOINT += '/'
|
||||
azure_endpoint = AZURE_ENDPOINT + f'openai/deployments/{AZURE_ENGINE}/chat/completions?api-version=2023-05-15'
|
||||
@@ -101,7 +97,6 @@ if cohere_endpoint in API_URL_REDIRECT: cohere_endpoint = API_URL_REDIRECT[coher
|
||||
if ollama_endpoint in API_URL_REDIRECT: ollama_endpoint = API_URL_REDIRECT[ollama_endpoint]
|
||||
if yimodel_endpoint in API_URL_REDIRECT: yimodel_endpoint = API_URL_REDIRECT[yimodel_endpoint]
|
||||
if deepseekapi_endpoint in API_URL_REDIRECT: deepseekapi_endpoint = API_URL_REDIRECT[deepseekapi_endpoint]
|
||||
if grok_model_endpoint in API_URL_REDIRECT: grok_model_endpoint = API_URL_REDIRECT[grok_model_endpoint]
|
||||
|
||||
# 获取tokenizer
|
||||
tokenizer_gpt35 = LazyloadTiktoken("gpt-3.5-turbo")
|
||||
@@ -217,16 +212,6 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
"chatgpt-4o-latest": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"has_multimodal_capacity": True,
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
"gpt-4o-2024-05-13": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
@@ -273,9 +258,7 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
"openai_disable_system_prompt": True,
|
||||
"openai_disable_stream": True,
|
||||
"openai_force_temperature_one": True,
|
||||
},
|
||||
|
||||
"o1-mini": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
@@ -285,31 +268,6 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
"openai_disable_system_prompt": True,
|
||||
"openai_disable_stream": True,
|
||||
"openai_force_temperature_one": True,
|
||||
},
|
||||
|
||||
"o1-2024-12-17": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 200000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
"openai_disable_system_prompt": True,
|
||||
"openai_disable_stream": True,
|
||||
"openai_force_temperature_one": True,
|
||||
},
|
||||
|
||||
"o1": {
|
||||
"fn_with_ui": chatgpt_ui,
|
||||
"fn_without_ui": chatgpt_noui,
|
||||
"endpoint": openai_endpoint,
|
||||
"max_token": 200000,
|
||||
"tokenizer": tokenizer_gpt4,
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
"openai_disable_system_prompt": True,
|
||||
"openai_disable_stream": True,
|
||||
"openai_force_temperature_one": True,
|
||||
},
|
||||
|
||||
"gpt-4-turbo": {
|
||||
@@ -446,7 +404,6 @@ model_info = {
|
||||
"token_cnt": get_token_num_gpt4,
|
||||
},
|
||||
|
||||
# ChatGLM本地模型
|
||||
# 将 chatglm 直接对齐到 chatglm2
|
||||
"chatglm": {
|
||||
"fn_with_ui": chatglm_ui,
|
||||
@@ -472,14 +429,6 @@ model_info = {
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"chatglm4": {
|
||||
"fn_with_ui": chatglm4_ui,
|
||||
"fn_without_ui": chatglm4_noui,
|
||||
"endpoint": None,
|
||||
"max_token": 8192,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"qianfan": {
|
||||
"fn_with_ui": qianfan_ui,
|
||||
"fn_without_ui": qianfan_noui,
|
||||
@@ -812,8 +761,7 @@ if "qwen-local" in AVAIL_LLM_MODELS:
|
||||
except:
|
||||
logger.error(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 通义-在线模型 -=-=-=-=-=-=-
|
||||
qwen_models = ["qwen-max-latest", "qwen-max-2025-01-25","qwen-max","qwen-turbo","qwen-plus"]
|
||||
if any(item in qwen_models for item in AVAIL_LLM_MODELS):
|
||||
if "qwen-turbo" in AVAIL_LLM_MODELS or "qwen-plus" in AVAIL_LLM_MODELS or "qwen-max" in AVAIL_LLM_MODELS: # zhipuai
|
||||
try:
|
||||
from .bridge_qwen import predict_no_ui_long_connection as qwen_noui
|
||||
from .bridge_qwen import predict as qwen_ui
|
||||
@@ -823,7 +771,7 @@ if any(item in qwen_models for item in AVAIL_LLM_MODELS):
|
||||
"fn_without_ui": qwen_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 100000,
|
||||
"max_token": 6144,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
@@ -832,7 +780,7 @@ if any(item in qwen_models for item in AVAIL_LLM_MODELS):
|
||||
"fn_without_ui": qwen_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 129024,
|
||||
"max_token": 30720,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
@@ -841,25 +789,7 @@ if any(item in qwen_models for item in AVAIL_LLM_MODELS):
|
||||
"fn_without_ui": qwen_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 30720,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"qwen-max-latest": {
|
||||
"fn_with_ui": qwen_ui,
|
||||
"fn_without_ui": qwen_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 30720,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"qwen-max-2025-01-25": {
|
||||
"fn_with_ui": qwen_ui,
|
||||
"fn_without_ui": qwen_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": None,
|
||||
"max_token": 30720,
|
||||
"max_token": 28672,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
}
|
||||
@@ -946,31 +876,6 @@ if any(item in yi_models for item in AVAIL_LLM_MODELS):
|
||||
})
|
||||
except:
|
||||
logger.error(trimmed_format_exc())
|
||||
|
||||
|
||||
# -=-=-=-=-=-=- Grok model from x.ai -=-=-=-=-=-=-
|
||||
grok_models = ["grok-beta"]
|
||||
if any(item in grok_models for item in AVAIL_LLM_MODELS):
|
||||
try:
|
||||
grok_beta_128k_noui, grok_beta_128k_ui = get_predict_function(
|
||||
api_key_conf_name="GROK_API_KEY", max_output_token=8192, disable_proxy=False
|
||||
)
|
||||
|
||||
model_info.update({
|
||||
"grok-beta": {
|
||||
"fn_with_ui": grok_beta_128k_ui,
|
||||
"fn_without_ui": grok_beta_128k_noui,
|
||||
"can_multi_thread": True,
|
||||
"endpoint": grok_model_endpoint,
|
||||
"max_token": 128000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
|
||||
})
|
||||
except:
|
||||
logger.error(trimmed_format_exc())
|
||||
|
||||
# -=-=-=-=-=-=- 讯飞星火认知大模型 -=-=-=-=-=-=-
|
||||
if "spark" in AVAIL_LLM_MODELS:
|
||||
try:
|
||||
@@ -1072,7 +977,7 @@ if "zhipuai" in AVAIL_LLM_MODELS: # zhipuai 是glm-4的别名，向后兼容
|
||||
})
|
||||
except:
|
||||
logger.error(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 幻方-深度求索本地大模型 -=-=-=-=-=-=-
|
||||
# -=-=-=-=-=-=- 幻方-深度求索大模型 -=-=-=-=-=-=-
|
||||
if "deepseekcoder" in AVAIL_LLM_MODELS: # deepseekcoder
|
||||
try:
|
||||
from .bridge_deepseekcoder import predict_no_ui_long_connection as deepseekcoder_noui
|
||||
@@ -1090,7 +995,7 @@ if "deepseekcoder" in AVAIL_LLM_MODELS: # deepseekcoder
|
||||
except:
|
||||
logger.error(trimmed_format_exc())
|
||||
# -=-=-=-=-=-=- 幻方-深度求索大模型在线API -=-=-=-=-=-=-
|
||||
if "deepseek-chat" in AVAIL_LLM_MODELS or "deepseek-coder" in AVAIL_LLM_MODELS or "deepseek-reasoner" in AVAIL_LLM_MODELS:
|
||||
if "deepseek-chat" in AVAIL_LLM_MODELS or "deepseek-coder" in AVAIL_LLM_MODELS:
|
||||
try:
|
||||
deepseekapi_noui, deepseekapi_ui = get_predict_function(
|
||||
api_key_conf_name="DEEPSEEK_API_KEY", max_output_token=4096, disable_proxy=False
|
||||
@@ -1101,7 +1006,7 @@ if "deepseek-chat" in AVAIL_LLM_MODELS or "deepseek-coder" in AVAIL_LLM_MODELS o
|
||||
"fn_without_ui": deepseekapi_noui,
|
||||
"endpoint": deepseekapi_endpoint,
|
||||
"can_multi_thread": True,
|
||||
"max_token": 64000,
|
||||
"max_token": 32000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
@@ -1114,16 +1019,6 @@ if "deepseek-chat" in AVAIL_LLM_MODELS or "deepseek-coder" in AVAIL_LLM_MODELS o
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
},
|
||||
"deepseek-reasoner":{
|
||||
"fn_with_ui": deepseekapi_ui,
|
||||
"fn_without_ui": deepseekapi_noui,
|
||||
"endpoint": deepseekapi_endpoint,
|
||||
"can_multi_thread": True,
|
||||
"max_token": 64000,
|
||||
"tokenizer": tokenizer_gpt35,
|
||||
"token_cnt": get_token_num_gpt35,
|
||||
"enable_reasoning": True
|
||||
},
|
||||
})
|
||||
except:
|
||||
logger.error(trimmed_format_exc())
|
||||
@@ -1265,9 +1160,9 @@ def LLM_CATCH_EXCEPTION(f):
|
||||
"""
|
||||
装饰器函数，将错误显示出来
|
||||
"""
|
||||
def decorated(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list, console_silence:bool):
|
||||
def decorated(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list, console_slience:bool):
|
||||
try:
|
||||
return f(inputs, llm_kwargs, history, sys_prompt, observe_window, console_silence)
|
||||
return f(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience)
|
||||
except Exception as e:
|
||||
tb_str = '\n```\n' + trimmed_format_exc() + '\n```\n'
|
||||
observe_window[0] = tb_str
|
||||
@@ -1275,7 +1170,7 @@ def LLM_CATCH_EXCEPTION(f):
|
||||
return decorated
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list=[], console_silence:bool=False):
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys_prompt:str, observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
发送至LLM，等待回复，一次性完成，不显示中间过程。但内部（尽可能地）用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
@@ -1297,7 +1192,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys
|
||||
if '&' not in model:
|
||||
# 如果只询问“一个”大语言模型（多数情况）：
|
||||
method = model_info[model]["fn_without_ui"]
|
||||
return method(inputs, llm_kwargs, history, sys_prompt, observe_window, console_silence)
|
||||
return method(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience)
|
||||
else:
|
||||
# 如果同时询问“多个”大语言模型，这个稍微啰嗦一点，但思路相同，您不必读这个else分支
|
||||
executor = ThreadPoolExecutor(max_workers=4)
|
||||
@@ -1314,7 +1209,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list, sys
|
||||
method = model_info[model]["fn_without_ui"]
|
||||
llm_kwargs_feedin = copy.deepcopy(llm_kwargs)
|
||||
llm_kwargs_feedin['llm_model'] = model
|
||||
future = executor.submit(LLM_CATCH_EXCEPTION(method), inputs, llm_kwargs_feedin, history, sys_prompt, window_mutex[i], console_silence)
|
||||
future = executor.submit(LLM_CATCH_EXCEPTION(method), inputs, llm_kwargs_feedin, history, sys_prompt, window_mutex[i], console_slience)
|
||||
futures.append(future)
|
||||
|
||||
def mutex_manager(window_mutex, observe_window):
|
||||
@@ -1391,11 +1286,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot,
|
||||
|
||||
inputs = apply_gpt_academic_string_mask(inputs, mode="show_llm")
|
||||
|
||||
if llm_kwargs['llm_model'] not in model_info:
|
||||
from toolbox import update_ui
|
||||
chatbot.append([inputs, f"很抱歉，模型 '{llm_kwargs['llm_model']}' 暂不支持<br/>(1) 检查config中的AVAIL_LLM_MODELS选项<br/>(2) 检查request_llms/bridge_all.py中的模型路由"])
|
||||
yield from update_ui(chatbot=chatbot, history=history) # 刷新界面
|
||||
|
||||
method = model_info[llm_kwargs['llm_model']]["fn_with_ui"] # 如果这里报错，检查config中的AVAIL_LLM_MODELS选项
|
||||
|
||||
if additional_fn: # 根据基础功能区 ModelOverride 参数调整模型类型
|
||||
|
||||
@@ -23,33 +23,39 @@ class GetGLM3Handle(LocalLLMHandle):
|
||||
import os
|
||||
import platform
|
||||
|
||||
LOCAL_MODEL_PATH, LOCAL_MODEL_QUANT, device = get_conf("CHATGLM_LOCAL_MODEL_PATH", "LOCAL_MODEL_QUANT", "LOCAL_MODEL_DEVICE")
|
||||
model_path = LOCAL_MODEL_PATH
|
||||
LOCAL_MODEL_QUANT, device = get_conf("LOCAL_MODEL_QUANT", "LOCAL_MODEL_DEVICE")
|
||||
_model_name_ = "THUDM/chatglm3-6b"
|
||||
# if LOCAL_MODEL_QUANT == "INT4": # INT4
|
||||
# _model_name_ = "THUDM/chatglm3-6b-int4"
|
||||
# elif LOCAL_MODEL_QUANT == "INT8": # INT8
|
||||
# _model_name_ = "THUDM/chatglm3-6b-int8"
|
||||
# else:
|
||||
# _model_name_ = "THUDM/chatglm3-6b" # FP16
|
||||
with ProxyNetworkActivate("Download_LLM"):
|
||||
chatglm_tokenizer = AutoTokenizer.from_pretrained(
|
||||
model_path, trust_remote_code=True
|
||||
_model_name_, trust_remote_code=True
|
||||
)
|
||||
if device == "cpu":
|
||||
chatglm_model = AutoModel.from_pretrained(
|
||||
model_path,
|
||||
_model_name_,
|
||||
trust_remote_code=True,
|
||||
device="cpu",
|
||||
).float()
|
||||
elif LOCAL_MODEL_QUANT == "INT4": # INT4
|
||||
chatglm_model = AutoModel.from_pretrained(
|
||||
pretrained_model_name_or_path=model_path,
|
||||
pretrained_model_name_or_path=_model_name_,
|
||||
trust_remote_code=True,
|
||||
quantization_config=BitsAndBytesConfig(load_in_4bit=True),
|
||||
)
|
||||
elif LOCAL_MODEL_QUANT == "INT8": # INT8
|
||||
chatglm_model = AutoModel.from_pretrained(
|
||||
pretrained_model_name_or_path=model_path,
|
||||
pretrained_model_name_or_path=_model_name_,
|
||||
trust_remote_code=True,
|
||||
quantization_config=BitsAndBytesConfig(load_in_8bit=True),
|
||||
)
|
||||
else:
|
||||
chatglm_model = AutoModel.from_pretrained(
|
||||
pretrained_model_name_or_path=model_path,
|
||||
pretrained_model_name_or_path=_model_name_,
|
||||
trust_remote_code=True,
|
||||
device="cuda",
|
||||
)
|
||||
|
||||
@@ -1,81 +0,0 @@
|
||||
model_name = "ChatGLM4"
|
||||
cmd_to_install = """
|
||||
`pip install -r request_llms/requirements_chatglm4.txt`
|
||||
`pip install modelscope`
|
||||
`modelscope download --model ZhipuAI/glm-4-9b-chat --local_dir ./THUDM/glm-4-9b-chat`
|
||||
"""
|
||||
|
||||
|
||||
from toolbox import get_conf, ProxyNetworkActivate
|
||||
from .local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
# 🔌💻 Local Model
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
class GetGLM4Handle(LocalLLMHandle):
|
||||
|
||||
def load_model_info(self):
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
self.model_name = model_name
|
||||
self.cmd_to_install = cmd_to_install
|
||||
|
||||
def load_model_and_tokenizer(self):
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
import torch
|
||||
from transformers import AutoModel, AutoModelForCausalLM, AutoTokenizer
|
||||
import os
|
||||
|
||||
LOCAL_MODEL_PATH, device = get_conf("CHATGLM_LOCAL_MODEL_PATH", "LOCAL_MODEL_DEVICE")
|
||||
model_path = LOCAL_MODEL_PATH
|
||||
chatglm_tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)
|
||||
chatglm_model = AutoModelForCausalLM.from_pretrained(
|
||||
model_path,
|
||||
torch_dtype=torch.bfloat16,
|
||||
low_cpu_mem_usage=True,
|
||||
trust_remote_code=True,
|
||||
device=device
|
||||
).eval().to(device)
|
||||
self._model = chatglm_model
|
||||
self._tokenizer = chatglm_tokenizer
|
||||
return self._model, self._tokenizer
|
||||
|
||||
|
||||
def llm_stream_generator(self, **kwargs):
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
def adaptor(kwargs):
|
||||
query = kwargs["query"]
|
||||
max_length = kwargs["max_length"]
|
||||
top_p = kwargs["top_p"]
|
||||
temperature = kwargs["temperature"]
|
||||
history = kwargs["history"]
|
||||
return query, max_length, top_p, temperature, history
|
||||
|
||||
query, max_length, top_p, temperature, history = adaptor(kwargs)
|
||||
inputs = self._tokenizer.apply_chat_template([{"role": "user", "content": query}],
|
||||
add_generation_prompt=True,
|
||||
tokenize=True,
|
||||
return_tensors="pt",
|
||||
return_dict=True
|
||||
).to(self._model.device)
|
||||
gen_kwargs = {"max_length": max_length, "do_sample": True, "top_k": top_p}
|
||||
|
||||
outputs = self._model.generate(**inputs, **gen_kwargs)
|
||||
outputs = outputs[:, inputs['input_ids'].shape[1]:]
|
||||
response = self._tokenizer.decode(outputs[0], skip_special_tokens=True)
|
||||
yield response
|
||||
|
||||
def try_to_import_special_deps(self, **kwargs):
|
||||
# import something that will raise error if the user does not install requirement_*.txt
|
||||
# 🏃♂️🏃♂️🏃♂️ 主进程执行
|
||||
import importlib
|
||||
|
||||
# importlib.import_module('modelscope')
|
||||
|
||||
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
# 🔌💻 GPT-Academic Interface
|
||||
# ------------------------------------------------------------------------------------------------------------------------
|
||||
predict_no_ui_long_connection, predict = get_local_llm_predict_fns(
|
||||
GetGLM4Handle, model_name, history_format="chatglm3"
|
||||
)
|
||||
@@ -139,7 +139,7 @@ global glmft_handle
|
||||
glmft_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -23,13 +23,8 @@ from loguru import logger
|
||||
from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history
|
||||
from toolbox import trimmed_format_exc, is_the_upload_folder, read_one_api_model_name, log_chat
|
||||
from toolbox import ChatBotWithCookies, have_any_recent_upload_image_files, encode_image
|
||||
proxies, WHEN_TO_USE_PROXY, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
|
||||
get_conf('proxies', 'WHEN_TO_USE_PROXY', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
|
||||
|
||||
if "Connect_OpenAI" not in WHEN_TO_USE_PROXY:
|
||||
if proxies is not None:
|
||||
logger.error("虽然您配置了代理设置，但不会在连接OpenAI的过程中起作用，请检查WHEN_TO_USE_PROXY配置。")
|
||||
proxies = None
|
||||
proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
|
||||
get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY', 'API_ORG', 'AZURE_CFG_ARRAY')
|
||||
|
||||
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
|
||||
'网络错误，检查代理服务器是否可用，以及代理设置的格式是否正确，格式须是[协议]://[地址]:[端口]，缺一不可。'
|
||||
@@ -125,7 +120,7 @@ def verify_endpoint(endpoint):
|
||||
raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
|
||||
return endpoint
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_silence:bool=False):
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_slience:bool=False):
|
||||
"""
|
||||
发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
@@ -185,25 +180,19 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
||||
raise ConnectionAbortedError("正常结束，但显示Token不足，导致输出不完整，请削减单次输入的文本量。")
|
||||
else:
|
||||
raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
|
||||
if ('data: [DONE]' in chunk_decoded): break # api2d & one-api 正常完成
|
||||
if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成
|
||||
# 提前读取一些信息 （用于判断异常）
|
||||
if has_choices and not choice_valid:
|
||||
# 一些垃圾第三方接口的出现这样的错误
|
||||
continue
|
||||
json_data = chunkjson['choices'][0]
|
||||
delta = json_data["delta"]
|
||||
|
||||
if len(delta) == 0:
|
||||
is_termination_certain = False
|
||||
if (has_choices) and (chunkjson['choices'][0].get('finish_reason', 'null') == 'stop'): is_termination_certain = True
|
||||
if is_termination_certain: break
|
||||
else: continue # 对于不符合规范的狗屎接口，这里需要继续
|
||||
|
||||
if len(delta) == 0: break
|
||||
if (not has_content) and has_role: continue
|
||||
if (not has_content) and (not has_role): continue # raise RuntimeError("发现不标准的第三方接口："+delta)
|
||||
if has_content: # has_role = True/False
|
||||
result += delta["content"]
|
||||
if not console_silence: print(delta["content"], end='')
|
||||
if not console_slience: print(delta["content"], end='')
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1:
|
||||
@@ -231,7 +220,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yield出去，可以直接修改对话界面内容
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
from request_llms.bridge_all import model_info
|
||||
@@ -296,8 +285,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
history.extend([inputs, ""])
|
||||
|
||||
retry = 0
|
||||
previous_ui_reflesh_time = 0
|
||||
ui_reflesh_min_interval = 0.0
|
||||
while True:
|
||||
try:
|
||||
# make a POST request to the API endpoint, stream=True
|
||||
@@ -310,13 +297,13 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="请求超时"+retry_msg) # 刷新界面
|
||||
if retry > MAX_RETRY: raise TimeoutError
|
||||
|
||||
|
||||
if not stream:
|
||||
# 该分支仅适用于不支持stream的o1模型，其他情形一律不适用
|
||||
yield from handle_o1_model_special(response, inputs, llm_kwargs, chatbot, history)
|
||||
return
|
||||
|
||||
if stream:
|
||||
reach_termination = False # 处理一些 new-api 的奇葩异常
|
||||
gpt_replying_buffer = ""
|
||||
is_head_of_the_stream = True
|
||||
stream_response = response.iter_lines()
|
||||
@@ -329,14 +316,11 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
error_msg = chunk_decoded
|
||||
# 首先排除一个one-api没有done数据包的第三方Bug情形
|
||||
if len(gpt_replying_buffer.strip()) > 0 and len(error_msg) == 0:
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="检测到有缺陷的接口，建议选择更稳定的接口。")
|
||||
if not reach_termination:
|
||||
reach_termination = True
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="检测到有缺陷的非OpenAI官方接口，建议选择更稳定的接口。")
|
||||
break
|
||||
# 其他情况，直接返回报错
|
||||
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="接口返回了错误:" + chunk.decode()) # 刷新界面
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="非OpenAI官方接口返回了错误:" + chunk.decode()) # 刷新界面
|
||||
return
|
||||
|
||||
# 提前读取一些信息 （用于判断异常）
|
||||
@@ -346,8 +330,6 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
# 数据流的第一帧不携带content
|
||||
is_head_of_the_stream = False; continue
|
||||
|
||||
if "error" in chunk_decoded: logger.error(f"接口返回了未知错误: {chunk_decoded}")
|
||||
|
||||
if chunk:
|
||||
try:
|
||||
if has_choices and not choice_valid:
|
||||
@@ -356,25 +338,14 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
if ('data: [DONE]' not in chunk_decoded) and len(chunk_decoded) > 0 and (chunkjson is None):
|
||||
# 传递进来一些奇怪的东西
|
||||
raise ValueError(f'无法读取以下数据，请检查配置。\n\n{chunk_decoded}')
|
||||
# 前者是API2D & One-API的结束条件，后者是OPENAI的结束条件
|
||||
one_api_terminate = ('data: [DONE]' in chunk_decoded)
|
||||
openai_terminate = (has_choices) and (len(chunkjson['choices'][0]["delta"]) == 0)
|
||||
if one_api_terminate or openai_terminate:
|
||||
is_termination_certain = False
|
||||
if one_api_terminate: is_termination_certain = True # 抓取符合规范的结束条件
|
||||
elif (has_choices) and (chunkjson['choices'][0].get('finish_reason', 'null') == 'stop'): is_termination_certain = True # 抓取符合规范的结束条件
|
||||
if is_termination_certain:
|
||||
reach_termination = True
|
||||
# 前者是API2D的结束条件，后者是OPENAI的结束条件
|
||||
if ('data: [DONE]' in chunk_decoded) or (len(chunkjson['choices'][0]["delta"]) == 0):
|
||||
# 判定为数据流的结束，gpt_replying_buffer也写完了
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
||||
break # 对于符合规范的接口，这里可以break
|
||||
else:
|
||||
continue # 对于不符合规范的狗屎接口，这里需要继续
|
||||
# 到这里，我们已经可以假定必须包含choice了
|
||||
try:
|
||||
status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
|
||||
except:
|
||||
logger.error(f"一些垃圾第三方接口出现这样的错误，兼容一下吧: {chunk_decoded}")
|
||||
break
|
||||
# 处理数据流的主体
|
||||
status_text = f"finish_reason: {chunkjson['choices'][0].get('finish_reason', 'null')}"
|
||||
# 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
|
||||
if has_content:
|
||||
# 正常情况
|
||||
gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
|
||||
@@ -383,26 +354,21 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
continue
|
||||
else:
|
||||
# 至此已经超出了正常接口应该进入的范围，一些垃圾第三方接口会出现这样的错误
|
||||
if chunkjson['choices'][0]["delta"].get("content", None) is None:
|
||||
logger.error(f"一些垃圾第三方接口出现这样的错误，兼容一下吧: {chunk_decoded}")
|
||||
continue
|
||||
if chunkjson['choices'][0]["delta"]["content"] is None: continue # 一些垃圾第三方接口出现这样的错误，兼容一下吧
|
||||
gpt_replying_buffer = gpt_replying_buffer + chunkjson['choices'][0]["delta"]["content"]
|
||||
|
||||
history[-1] = gpt_replying_buffer
|
||||
chatbot[-1] = (history[-2], history[-1])
|
||||
if time.time() - previous_ui_reflesh_time > ui_reflesh_min_interval:
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg=status_text) # 刷新界面
|
||||
previous_ui_reflesh_time = time.time()
|
||||
except Exception as e:
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析不合常规") # 刷新界面
|
||||
chunk = get_full_error(chunk, stream_response)
|
||||
chunk_decoded = chunk.decode()
|
||||
error_msg = chunk_decoded
|
||||
chatbot, history = handle_error(inputs, llm_kwargs, chatbot, history, chunk_decoded, error_msg)
|
||||
logger.error(error_msg)
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="Json解析异常" + error_msg) # 刷新界面
|
||||
logger.error(error_msg)
|
||||
return
|
||||
yield from update_ui(chatbot=chatbot, history=history, msg="完成") # 刷新界面
|
||||
return # return from stream-branch
|
||||
|
||||
def handle_o1_model_special(response, inputs, llm_kwargs, chatbot, history):
|
||||
@@ -570,8 +536,6 @@ def generate_payload(inputs:str, llm_kwargs:dict, history:list, system_prompt:st
|
||||
"n": 1,
|
||||
"stream": stream,
|
||||
}
|
||||
openai_force_temperature_one = model_info[llm_kwargs['llm_model']].get('openai_force_temperature_one', False)
|
||||
if openai_force_temperature_one:
|
||||
payload.pop('temperature')
|
||||
|
||||
return headers,payload
|
||||
|
||||
|
||||
@@ -16,7 +16,7 @@ import base64
|
||||
import glob
|
||||
from loguru import logger
|
||||
from toolbox import get_conf, update_ui, is_any_api_key, select_api_key, what_keys, clip_history, trimmed_format_exc, is_the_upload_folder, \
|
||||
update_ui_latest_msg, get_max_token, encode_image, have_any_recent_upload_image_files, log_chat
|
||||
update_ui_lastest_msg, get_max_token, encode_image, have_any_recent_upload_image_files, log_chat
|
||||
|
||||
|
||||
proxies, TIMEOUT_SECONDS, MAX_RETRY, API_ORG, AZURE_CFG_ARRAY = \
|
||||
@@ -67,7 +67,7 @@ def verify_endpoint(endpoint):
|
||||
"""
|
||||
return endpoint
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_silence=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
|
||||
raise NotImplementedError
|
||||
|
||||
|
||||
@@ -183,7 +183,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
if ('data: [DONE]' in chunk_decoded) or (len(chunkjson['choices'][0]["delta"]) == 0):
|
||||
# 判定为数据流的结束，gpt_replying_buffer也写完了
|
||||
lastmsg = chatbot[-1][-1] + f"\n\n\n\n「{llm_kwargs['llm_model']}调用结束，该模型不具备上下文对话能力，如需追问，请及时切换模型。」"
|
||||
yield from update_ui_latest_msg(lastmsg, chatbot, history, delay=1)
|
||||
yield from update_ui_lastest_msg(lastmsg, chatbot, history, delay=1)
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_replying_buffer)
|
||||
break
|
||||
# 处理数据流的主体
|
||||
|
||||
@@ -69,7 +69,7 @@ def decode_chunk(chunk):
|
||||
return need_to_pass, chunkjson, is_last_chunk
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_silence=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
|
||||
"""
|
||||
发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
@@ -151,7 +151,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yield出去，可以直接修改对话界面内容
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
if inputs == "": inputs = "空空如也的输入栏"
|
||||
|
||||
@@ -68,7 +68,7 @@ def verify_endpoint(endpoint):
|
||||
raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
|
||||
return endpoint
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_silence:bool=False):
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_slience:bool=False):
|
||||
"""
|
||||
发送，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
@@ -111,7 +111,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
||||
if chunkjson['event_type'] == 'stream-start': continue
|
||||
if chunkjson['event_type'] == 'text-generation':
|
||||
result += chunkjson["text"]
|
||||
if not console_silence: print(chunkjson["text"], end='')
|
||||
if not console_slience: print(chunkjson["text"], end='')
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1:
|
||||
@@ -132,7 +132,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yield出去，可以直接修改对话界面内容
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
# if is_any_api_key(inputs):
|
||||
|
||||
@@ -6,6 +6,7 @@ from toolbox import get_conf
|
||||
from request_llms.local_llm_class import LocalLLMHandle, get_local_llm_predict_fns
|
||||
from threading import Thread
|
||||
from loguru import logger
|
||||
import torch
|
||||
import os
|
||||
|
||||
def download_huggingface_model(model_name, max_retry, local_dir):
|
||||
@@ -28,7 +29,6 @@ class GetCoderLMHandle(LocalLLMHandle):
|
||||
self.cmd_to_install = cmd_to_install
|
||||
|
||||
def load_model_and_tokenizer(self):
|
||||
import torch
|
||||
# 🏃♂️🏃♂️🏃♂️ 子进程执行
|
||||
with ProxyNetworkActivate('Download_LLM'):
|
||||
from transformers import AutoTokenizer, AutoModelForCausalLM, TextIteratorStreamer
|
||||
|
||||
@@ -8,7 +8,7 @@ import os
|
||||
import time
|
||||
from request_llms.com_google import GoogleChatInit
|
||||
from toolbox import ChatBotWithCookies
|
||||
from toolbox import get_conf, update_ui, update_ui_latest_msg, have_any_recent_upload_image_files, trimmed_format_exc, log_chat, encode_image
|
||||
from toolbox import get_conf, update_ui, update_ui_lastest_msg, have_any_recent_upload_image_files, trimmed_format_exc, log_chat, encode_image
|
||||
|
||||
proxies, TIMEOUT_SECONDS, MAX_RETRY = get_conf('proxies', 'TIMEOUT_SECONDS', 'MAX_RETRY')
|
||||
timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check proxy settings in config.py.' + \
|
||||
@@ -16,7 +16,7 @@ timeout_bot_msg = '[Local Message] Request timeout. Network error. Please check
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=[],
|
||||
console_silence:bool=False):
|
||||
console_slience:bool=False):
|
||||
# 检查API_KEY
|
||||
if get_conf("GEMINI_API_KEY") == "":
|
||||
raise ValueError(f"请配置 GEMINI_API_KEY。")
|
||||
@@ -60,7 +60,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
|
||||
# 检查API_KEY
|
||||
if get_conf("GEMINI_API_KEY") == "":
|
||||
yield from update_ui_latest_msg(f"请配置 GEMINI_API_KEY。", chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(f"请配置 GEMINI_API_KEY。", chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
# 适配润色区域
|
||||
|
||||
@@ -55,7 +55,7 @@ class GetGLMHandle(Process):
|
||||
if self.jittorllms_model is None:
|
||||
device = get_conf('LOCAL_MODEL_DEVICE')
|
||||
from .jittorllms.models import get_model
|
||||
# available_models = ["chatglm", "pangualpha", "llama", "chatrwkv"]
|
||||
# availabel_models = ["chatglm", "pangualpha", "llama", "chatrwkv"]
|
||||
args_dict = {'model': 'llama'}
|
||||
print('self.jittorllms_model = get_model(types.SimpleNamespace(**args_dict))')
|
||||
self.jittorllms_model = get_model(types.SimpleNamespace(**args_dict))
|
||||
@@ -107,7 +107,7 @@ global llama_glm_handle
|
||||
llama_glm_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -55,7 +55,7 @@ class GetGLMHandle(Process):
|
||||
if self.jittorllms_model is None:
|
||||
device = get_conf('LOCAL_MODEL_DEVICE')
|
||||
from .jittorllms.models import get_model
|
||||
# available_models = ["chatglm", "pangualpha", "llama", "chatrwkv"]
|
||||
# availabel_models = ["chatglm", "pangualpha", "llama", "chatrwkv"]
|
||||
args_dict = {'model': 'pangualpha'}
|
||||
print('self.jittorllms_model = get_model(types.SimpleNamespace(**args_dict))')
|
||||
self.jittorllms_model = get_model(types.SimpleNamespace(**args_dict))
|
||||
@@ -107,7 +107,7 @@ global pangu_glm_handle
|
||||
pangu_glm_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -55,7 +55,7 @@ class GetGLMHandle(Process):
|
||||
if self.jittorllms_model is None:
|
||||
device = get_conf('LOCAL_MODEL_DEVICE')
|
||||
from .jittorllms.models import get_model
|
||||
# available_models = ["chatglm", "pangualpha", "llama", "chatrwkv"]
|
||||
# availabel_models = ["chatglm", "pangualpha", "llama", "chatrwkv"]
|
||||
args_dict = {'model': 'chatrwkv'}
|
||||
print('self.jittorllms_model = get_model(types.SimpleNamespace(**args_dict))')
|
||||
self.jittorllms_model = get_model(types.SimpleNamespace(**args_dict))
|
||||
@@ -107,7 +107,7 @@ global rwkv_glm_handle
|
||||
rwkv_glm_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -26,7 +26,7 @@ class GetLlamaHandle(LocalLLMHandle):
|
||||
import platform
|
||||
huggingface_token, device = get_conf('HUGGINGFACE_ACCESS_TOKEN', 'LOCAL_MODEL_DEVICE')
|
||||
assert len(huggingface_token) != 0, "没有填写 HUGGINGFACE_ACCESS_TOKEN"
|
||||
with open(os.path.expanduser('~/.cache/huggingface/token'), 'w', encoding='utf8') as f:
|
||||
with open(os.path.expanduser('~/.cache/huggingface/token'), 'w') as f:
|
||||
f.write(huggingface_token)
|
||||
model_id = 'meta-llama/Llama-2-7b-chat-hf'
|
||||
with ProxyNetworkActivate('Download_LLM'):
|
||||
@@ -46,8 +46,8 @@ class GetLlamaHandle(LocalLLMHandle):
|
||||
top_p = kwargs['top_p']
|
||||
temperature = kwargs['temperature']
|
||||
history = kwargs['history']
|
||||
console_silence = kwargs.get('console_silence', True)
|
||||
return query, max_length, top_p, temperature, history, console_silence
|
||||
console_slience = kwargs.get('console_slience', True)
|
||||
return query, max_length, top_p, temperature, history, console_slience
|
||||
|
||||
def convert_messages_to_prompt(query, history):
|
||||
prompt = ""
|
||||
@@ -57,7 +57,7 @@ class GetLlamaHandle(LocalLLMHandle):
|
||||
prompt += f"\n[INST]{query}[/INST]"
|
||||
return prompt
|
||||
|
||||
query, max_length, top_p, temperature, history, console_silence = adaptor(kwargs)
|
||||
query, max_length, top_p, temperature, history, console_slience = adaptor(kwargs)
|
||||
prompt = convert_messages_to_prompt(query, history)
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-
|
||||
# code from transformers.llama
|
||||
@@ -72,9 +72,9 @@ class GetLlamaHandle(LocalLLMHandle):
|
||||
generated_text = ""
|
||||
for new_text in streamer:
|
||||
generated_text += new_text
|
||||
if not console_silence: print(new_text, end='')
|
||||
if not console_slience: print(new_text, end='')
|
||||
yield generated_text.lstrip(prompt_tk_back).rstrip("</s>")
|
||||
if not console_silence: print()
|
||||
if not console_slience: print()
|
||||
# =-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=-=--=-=-
|
||||
|
||||
def try_to_import_special_deps(self, **kwargs):
|
||||
|
||||
@@ -31,7 +31,7 @@ class MoonShotInit:
|
||||
files.append(f)
|
||||
for file in files:
|
||||
if file.split('.')[-1] in ['pdf']:
|
||||
with open(file, 'r', encoding='utf8') as fp:
|
||||
with open(file, 'r') as fp:
|
||||
from crazy_functions.crazy_utils import read_and_clean_pdf_text
|
||||
file_content, _ = read_and_clean_pdf_text(fp)
|
||||
what_ask.append({"role": "system", "content": file_content})
|
||||
@@ -169,7 +169,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
log_chat(llm_model=llm_kwargs["llm_model"], input_str=inputs, output_str=gpt_bro_result)
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None,
|
||||
console_silence=False):
|
||||
console_slience=False):
|
||||
gpt_bro_init = MoonShotInit()
|
||||
watch_dog_patience = 60 # 看门狗的耐心, 设置10秒即可
|
||||
stream_response = gpt_bro_init.generate_messages(inputs, llm_kwargs, history, sys_prompt, True)
|
||||
|
||||
@@ -95,7 +95,7 @@ class GetGLMHandle(Process):
|
||||
- Its responses must not be vague, accusatory, rude, controversial, off-topic, or defensive.
|
||||
- It should avoid giving subjective opinions but rely on objective facts or phrases like \"in this context a human might say...\", \"some people might think...\", etc.
|
||||
- Its responses must also be positive, polite, interesting, entertaining, and engaging.
|
||||
- It can provide additional relevant details to answer in-depth and comprehensively covering multiple aspects.
|
||||
- It can provide additional relevant details to answer in-depth and comprehensively covering mutiple aspects.
|
||||
- It apologizes and accepts the user's suggestion if the user corrects the incorrect answer generated by MOSS.
|
||||
Capabilities and tools that MOSS can possess.
|
||||
"""
|
||||
@@ -172,7 +172,7 @@ global moss_handle
|
||||
moss_handle = None
|
||||
#################################################################################
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -209,7 +209,7 @@ def predict_no_ui_long_connection(
|
||||
history=[],
|
||||
sys_prompt="",
|
||||
observe_window=[],
|
||||
console_silence=False,
|
||||
console_slience=False,
|
||||
):
|
||||
"""
|
||||
多线程方法
|
||||
|
||||
@@ -52,7 +52,7 @@ def decode_chunk(chunk):
|
||||
pass
|
||||
return chunk_decoded, chunkjson, is_last_chunk
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_silence=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="", observe_window=None, console_slience=False):
|
||||
"""
|
||||
发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
@@ -75,7 +75,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
|
||||
# make a POST request to the API endpoint, stream=False
|
||||
from .bridge_all import model_info
|
||||
endpoint = model_info[llm_kwargs['llm_model']]['endpoint']
|
||||
response = requests.post(endpoint, headers=headers, proxies=None,
|
||||
response = requests.post(endpoint, headers=headers, proxies=proxies,
|
||||
json=payload, stream=True, timeout=TIMEOUT_SECONDS); break
|
||||
except requests.exceptions.ReadTimeout as e:
|
||||
retry += 1
|
||||
@@ -99,7 +99,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history=[], sys_prompt="",
|
||||
logger.info(f'[response] {result}')
|
||||
break
|
||||
result += chunkjson['message']["content"]
|
||||
if not console_silence: print(chunkjson['message']["content"], end='')
|
||||
if not console_slience: print(chunkjson['message']["content"], end='')
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1:
|
||||
@@ -124,7 +124,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yield出去，可以直接修改对话界面内容
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
if inputs == "": inputs = "空空如也的输入栏"
|
||||
@@ -152,12 +152,10 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
history.append(inputs); history.append("")
|
||||
|
||||
retry = 0
|
||||
if proxies is not None:
|
||||
logger.error("Ollama不会使用代理服务器, 忽略了proxies的设置。")
|
||||
while True:
|
||||
try:
|
||||
# make a POST request to the API endpoint, stream=True
|
||||
response = requests.post(endpoint, headers=headers, proxies=None,
|
||||
response = requests.post(endpoint, headers=headers, proxies=proxies,
|
||||
json=payload, stream=True, timeout=TIMEOUT_SECONDS);break
|
||||
except:
|
||||
retry += 1
|
||||
|
||||
@@ -119,7 +119,7 @@ def verify_endpoint(endpoint):
|
||||
raise ValueError("Endpoint不正确, 请检查AZURE_ENDPOINT的配置! 当前的Endpoint为:" + endpoint)
|
||||
return endpoint
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_silence:bool=False):
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=None, console_slience:bool=False):
|
||||
"""
|
||||
发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
inputs：
|
||||
@@ -170,7 +170,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
chunk_decoded, chunkjson, has_choices, choice_valid, has_content, has_role = decode_chunk(chunk)
|
||||
if len(chunk_decoded)==0 or chunk_decoded.startswith(':'): continue
|
||||
if len(chunk_decoded)==0: continue
|
||||
if not chunk_decoded.startswith('data:'):
|
||||
error_msg = get_full_error(chunk, stream_response).decode()
|
||||
if "reduce the length" in error_msg:
|
||||
@@ -181,6 +181,9 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
||||
raise RuntimeError("OpenAI拒绝了请求：" + error_msg)
|
||||
if ('data: [DONE]' in chunk_decoded): break # api2d 正常完成
|
||||
# 提前读取一些信息 （用于判断异常）
|
||||
if (has_choices and not choice_valid) or ('OPENROUTER PROCESSING' in chunk_decoded):
|
||||
# 一些垃圾第三方接口的出现这样的错误，openrouter的特殊处理
|
||||
continue
|
||||
json_data = chunkjson['choices'][0]
|
||||
delta = json_data["delta"]
|
||||
if len(delta) == 0: break
|
||||
@@ -188,7 +191,7 @@ def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[],
|
||||
if (not has_content) and (not has_role): continue # raise RuntimeError("发现不标准的第三方接口："+delta)
|
||||
if has_content: # has_role = True/False
|
||||
result += delta["content"]
|
||||
if not console_silence: print(delta["content"], end='')
|
||||
if not console_slience: print(delta["content"], end='')
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1:
|
||||
@@ -213,7 +216,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yield出去，可以直接修改对话界面内容
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
from request_llms.bridge_all import model_info
|
||||
@@ -325,7 +328,8 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
|
||||
if chunk:
|
||||
try:
|
||||
if (has_choices and not choice_valid) or chunk_decoded.startswith(':'):
|
||||
if (has_choices and not choice_valid) or ('OPENROUTER PROCESSING' in chunk_decoded):
|
||||
# 一些垃圾第三方接口的出现这样的错误, 或者OPENROUTER的特殊处理,因为OPENROUTER的数据流未连接到模型时会出现OPENROUTER PROCESSING
|
||||
continue
|
||||
if ('data: [DONE]' not in chunk_decoded) and len(chunk_decoded) > 0 and (chunkjson is None):
|
||||
# 传递进来一些奇怪的东西
|
||||
@@ -512,7 +516,7 @@ def generate_payload(inputs:str, llm_kwargs:dict, history:list, system_prompt:st
|
||||
model, _ = read_one_api_model_name(model)
|
||||
if llm_kwargs['llm_model'].startswith('openrouter-'):
|
||||
model = llm_kwargs['llm_model'][len('openrouter-'):]
|
||||
model, _= read_one_api_model_name(model)
|
||||
model= read_one_api_model_name(model)
|
||||
if model == "gpt-3.5-random": # 随机选择, 绕过openai访问频率限制
|
||||
model = random.choice([
|
||||
"gpt-3.5-turbo",
|
||||
|
||||
@@ -121,7 +121,7 @@ def generate_from_baidu_qianfan(inputs, llm_kwargs, history, system_prompt):
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
|
||||
@@ -1,12 +1,12 @@
|
||||
import time
|
||||
import os
|
||||
from toolbox import update_ui, get_conf, update_ui_latest_msg
|
||||
from toolbox import update_ui, get_conf, update_ui_lastest_msg
|
||||
from toolbox import check_packages, report_exception, log_chat
|
||||
|
||||
model_name = 'Qwen'
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -35,13 +35,13 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
try:
|
||||
check_packages(["dashscope"])
|
||||
except:
|
||||
yield from update_ui_latest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade dashscope```。",
|
||||
yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade dashscope```。",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
# 检查DASHSCOPE_API_KEY
|
||||
if get_conf("DASHSCOPE_API_KEY") == "":
|
||||
yield from update_ui_latest_msg(f"请配置 DASHSCOPE_API_KEY。",
|
||||
yield from update_ui_lastest_msg(f"请配置 DASHSCOPE_API_KEY。",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
|
||||
@@ -1,5 +1,5 @@
|
||||
import time
|
||||
from toolbox import update_ui, get_conf, update_ui_latest_msg
|
||||
from toolbox import update_ui, get_conf, update_ui_lastest_msg
|
||||
from toolbox import check_packages, report_exception
|
||||
|
||||
model_name = '云雀大模型'
|
||||
@@ -10,7 +10,7 @@ def validate_key():
|
||||
return True
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
⭐ 多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -42,12 +42,12 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
try:
|
||||
check_packages(["zhipuai"])
|
||||
except:
|
||||
yield from update_ui_latest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade zhipuai```。",
|
||||
yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade zhipuai```。",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
if validate_key() is False:
|
||||
yield from update_ui_latest_msg(lastmsg="[Local Message] 请配置HUOSHAN_API_KEY", chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置HUOSHAN_API_KEY", chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
if additional_fn is not None:
|
||||
|
||||
@@ -2,7 +2,7 @@
|
||||
import time
|
||||
import threading
|
||||
import importlib
|
||||
from toolbox import update_ui, get_conf, update_ui_latest_msg
|
||||
from toolbox import update_ui, get_conf, update_ui_lastest_msg
|
||||
from multiprocessing import Process, Pipe
|
||||
|
||||
model_name = '星火认知大模型'
|
||||
@@ -14,7 +14,7 @@ def validate_key():
|
||||
return True
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -43,7 +43,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
if validate_key() is False:
|
||||
yield from update_ui_latest_msg(lastmsg="[Local Message] 请配置讯飞星火大模型的XFYUN_APPID, XFYUN_API_KEY, XFYUN_API_SECRET", chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置讯飞星火大模型的XFYUN_APPID, XFYUN_API_KEY, XFYUN_API_SECRET", chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
if additional_fn is not None:
|
||||
|
||||
@@ -225,7 +225,7 @@ def predict_no_ui_long_connection(
|
||||
history=[],
|
||||
sys_prompt="",
|
||||
observe_window=None,
|
||||
console_silence=False,
|
||||
console_slience=False,
|
||||
):
|
||||
"""
|
||||
多线程方法
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import time
|
||||
import os
|
||||
from toolbox import update_ui, get_conf, update_ui_latest_msg, log_chat
|
||||
from toolbox import update_ui, get_conf, update_ui_lastest_msg, log_chat
|
||||
from toolbox import check_packages, report_exception, have_any_recent_upload_image_files
|
||||
from toolbox import ChatBotWithCookies
|
||||
|
||||
@@ -13,7 +13,7 @@ def validate_key():
|
||||
return True
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -49,7 +49,7 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
yield from update_ui(chatbot=chatbot, history=history)
|
||||
|
||||
if validate_key() is False:
|
||||
yield from update_ui_latest_msg(lastmsg="[Local Message] 请配置ZHIPUAI_API_KEY", chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置ZHIPUAI_API_KEY", chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
if additional_fn is not None:
|
||||
|
||||
@@ -91,7 +91,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yield出去，可以直接修改对话界面内容
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
if additional_fn is not None:
|
||||
@@ -112,7 +112,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
|
||||
|
||||
mutable = ["", time.time()]
|
||||
def run_coroutine(mutable):
|
||||
def run_coorotine(mutable):
|
||||
async def get_result(mutable):
|
||||
# "tgui:galactica-1.3b@localhost:7860"
|
||||
|
||||
@@ -126,7 +126,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
break
|
||||
asyncio.run(get_result(mutable))
|
||||
|
||||
thread_listen = threading.Thread(target=run_coroutine, args=(mutable,), daemon=True)
|
||||
thread_listen = threading.Thread(target=run_coorotine, args=(mutable,), daemon=True)
|
||||
thread_listen.start()
|
||||
|
||||
while thread_listen.is_alive():
|
||||
@@ -142,7 +142,7 @@ def predict(inputs, llm_kwargs, plugin_kwargs, chatbot, history=[], system_promp
|
||||
|
||||
|
||||
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, observe_window, console_silence=False):
|
||||
def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, observe_window, console_slience=False):
|
||||
raw_input = "What I would like to say is the following: " + inputs
|
||||
prompt = raw_input
|
||||
tgui_say = ""
|
||||
@@ -151,7 +151,7 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
|
||||
addr, port = addr_port.split(':')
|
||||
|
||||
|
||||
def run_coroutine(observe_window):
|
||||
def run_coorotine(observe_window):
|
||||
async def get_result(observe_window):
|
||||
async for response in run(context=prompt, max_token=llm_kwargs['max_length'],
|
||||
temperature=llm_kwargs['temperature'],
|
||||
@@ -162,6 +162,6 @@ def predict_no_ui_long_connection(inputs, llm_kwargs, history, sys_prompt, obser
|
||||
print('exit when no listener')
|
||||
break
|
||||
asyncio.run(get_result(observe_window))
|
||||
thread_listen = threading.Thread(target=run_coroutine, args=(observe_window,))
|
||||
thread_listen = threading.Thread(target=run_coorotine, args=(observe_window,))
|
||||
thread_listen.start()
|
||||
return observe_window[0]
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import time
|
||||
import os
|
||||
from toolbox import update_ui, get_conf, update_ui_latest_msg, log_chat
|
||||
from toolbox import update_ui, get_conf, update_ui_lastest_msg, log_chat
|
||||
from toolbox import check_packages, report_exception, have_any_recent_upload_image_files
|
||||
from toolbox import ChatBotWithCookies
|
||||
|
||||
@@ -18,7 +18,7 @@ def make_media_input(inputs, image_paths):
|
||||
return inputs
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="",
|
||||
observe_window:list=[], console_silence:bool=False):
|
||||
observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
⭐多线程方法
|
||||
函数的说明请见 request_llms/bridge_all.py
|
||||
@@ -57,12 +57,12 @@ def predict(inputs:str, llm_kwargs:dict, plugin_kwargs:dict, chatbot:ChatBotWith
|
||||
try:
|
||||
check_packages(["zhipuai"])
|
||||
except:
|
||||
yield from update_ui_latest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade zhipuai```。",
|
||||
yield from update_ui_lastest_msg(f"导入软件依赖失败。使用该模型需要额外依赖，安装方法```pip install --upgrade zhipuai```。",
|
||||
chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
if validate_key() is False:
|
||||
yield from update_ui_latest_msg(lastmsg="[Local Message] 请配置ZHIPUAI_API_KEY", chatbot=chatbot, history=history, delay=0)
|
||||
yield from update_ui_lastest_msg(lastmsg="[Local Message] 请配置ZHIPUAI_API_KEY", chatbot=chatbot, history=history, delay=0)
|
||||
return
|
||||
|
||||
if additional_fn is not None:
|
||||
|
||||
@@ -202,24 +202,11 @@ class GoogleChatInit:
|
||||
) # 处理 history
|
||||
|
||||
messages.append(self.__conversation_user(inputs, llm_kwargs, enable_multimodal_capacity)) # 处理用户对话
|
||||
stop_sequences = str(llm_kwargs.get("stop", "")).split(" ")
|
||||
# 过滤空字符串并确保至少有一个停止序列
|
||||
stop_sequences = [s for s in stop_sequences if s]
|
||||
if not stop_sequences:
|
||||
payload = {
|
||||
"contents": messages,
|
||||
"generationConfig": {
|
||||
"temperature": llm_kwargs.get("temperature", 1),
|
||||
"topP": llm_kwargs.get("top_p", 0.8),
|
||||
"topK": 10,
|
||||
},
|
||||
}
|
||||
else:
|
||||
payload = {
|
||||
"contents": messages,
|
||||
"generationConfig": {
|
||||
# "maxOutputTokens": llm_kwargs.get("max_token", 1024),
|
||||
"stopSequences": stop_sequences,
|
||||
"stopSequences": str(llm_kwargs.get("stop", "")).split(" "),
|
||||
"temperature": llm_kwargs.get("temperature", 1),
|
||||
"topP": llm_kwargs.get("top_p", 0.8),
|
||||
"topK": 10,
|
||||
|
||||
@@ -24,13 +24,18 @@ class QwenRequestInstance():
|
||||
def generate(self, inputs, llm_kwargs, history, system_prompt):
|
||||
# import _thread as thread
|
||||
from dashscope import Generation
|
||||
QWEN_MODEL = {
|
||||
'qwen-turbo': Generation.Models.qwen_turbo,
|
||||
'qwen-plus': Generation.Models.qwen_plus,
|
||||
'qwen-max': Generation.Models.qwen_max,
|
||||
}[llm_kwargs['llm_model']]
|
||||
top_p = llm_kwargs.get('top_p', 0.8)
|
||||
if top_p == 0: top_p += 1e-5
|
||||
if top_p == 1: top_p -= 1e-5
|
||||
|
||||
self.result_buf = ""
|
||||
responses = Generation.call(
|
||||
model=llm_kwargs['llm_model'],
|
||||
model=QWEN_MODEL,
|
||||
messages=generate_message_payload(inputs, llm_kwargs, history, system_prompt),
|
||||
top_p=top_p,
|
||||
temperature=llm_kwargs.get('temperature', 1.0),
|
||||
|
||||
@@ -216,7 +216,7 @@ class LocalLLMHandle(Process):
|
||||
def get_local_llm_predict_fns(LLMSingletonClass, model_name, history_format='classic'):
|
||||
load_message = f"{model_name}尚未加载，加载需要一段时间。注意，取决于`config.py`的配置，{model_name}消耗大量的内存（CPU）或显存（GPU），也许会导致低配计算机卡死 ……"
|
||||
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=[], console_silence:bool=False):
|
||||
def predict_no_ui_long_connection(inputs:str, llm_kwargs:dict, history:list=[], sys_prompt:str="", observe_window:list=[], console_slience:bool=False):
|
||||
"""
|
||||
refer to request_llms/bridge_all.py
|
||||
"""
|
||||
|
||||
@@ -2,9 +2,15 @@ import json
|
||||
import time
|
||||
import traceback
|
||||
import requests
|
||||
|
||||
from loguru import logger
|
||||
from toolbox import get_conf, is_the_upload_folder, update_ui, update_ui_latest_msg
|
||||
|
||||
# config_private.py放自己的秘密如API和代理网址
|
||||
# 读取时首先看是否存在私密的config_private配置文件（不受git管控），如果有，则覆盖原config文件
|
||||
from toolbox import (
|
||||
get_conf,
|
||||
update_ui,
|
||||
is_the_upload_folder,
|
||||
)
|
||||
|
||||
proxies, TIMEOUT_SECONDS, MAX_RETRY = get_conf(
|
||||
"proxies", "TIMEOUT_SECONDS", "MAX_RETRY"
|
||||
@@ -30,50 +36,35 @@ def get_full_error(chunk, stream_response):
|
||||
|
||||
def decode_chunk(chunk):
|
||||
"""
|
||||
用于解读"content"和"finish_reason"的内容（如果支持思维链也会返回"reasoning_content"内容）
|
||||
用于解读"content"和"finish_reason"的内容
|
||||
"""
|
||||
chunk = chunk.decode()
|
||||
response = ""
|
||||
reasoning_content = ""
|
||||
respose = ""
|
||||
finish_reason = "False"
|
||||
|
||||
# 考虑返回类型是 text/json 和 text/event-stream 两种
|
||||
if chunk.startswith("data: "):
|
||||
chunk = chunk[6:]
|
||||
else:
|
||||
chunk = chunk
|
||||
|
||||
try:
|
||||
chunk = json.loads(chunk)
|
||||
chunk = json.loads(chunk[6:])
|
||||
except:
|
||||
response = ""
|
||||
respose = ""
|
||||
finish_reason = chunk
|
||||
|
||||
# 错误处理部分
|
||||
if "error" in chunk:
|
||||
response = "API_ERROR"
|
||||
respose = "API_ERROR"
|
||||
try:
|
||||
chunk = json.loads(chunk)
|
||||
finish_reason = chunk["error"]["code"]
|
||||
except:
|
||||
finish_reason = "API_ERROR"
|
||||
return response, reasoning_content, finish_reason
|
||||
return respose, finish_reason
|
||||
|
||||
try:
|
||||
if chunk["choices"][0]["delta"]["content"] is not None:
|
||||
response = chunk["choices"][0]["delta"]["content"]
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
if chunk["choices"][0]["delta"]["reasoning_content"] is not None:
|
||||
reasoning_content = chunk["choices"][0]["delta"]["reasoning_content"]
|
||||
respose = chunk["choices"][0]["delta"]["content"]
|
||||
except:
|
||||
pass
|
||||
try:
|
||||
finish_reason = chunk["choices"][0]["finish_reason"]
|
||||
except:
|
||||
pass
|
||||
return response, reasoning_content, finish_reason, str(chunk)
|
||||
return respose, finish_reason
|
||||
|
||||
|
||||
def generate_message(input, model, key, history, max_output_token, system_prompt, temperature):
|
||||
@@ -108,7 +99,7 @@ def generate_message(input, model, key, history, max_output_token, system_prompt
|
||||
what_i_ask_now["role"] = "user"
|
||||
what_i_ask_now["content"] = input
|
||||
messages.append(what_i_ask_now)
|
||||
payload = {
|
||||
playload = {
|
||||
"model": model,
|
||||
"messages": messages,
|
||||
"temperature": temperature,
|
||||
@@ -116,7 +107,7 @@ def generate_message(input, model, key, history, max_output_token, system_prompt
|
||||
"max_tokens": max_output_token,
|
||||
}
|
||||
|
||||
return headers, payload
|
||||
return headers, playload
|
||||
|
||||
|
||||
def get_predict_function(
|
||||
@@ -143,7 +134,7 @@ def get_predict_function(
|
||||
history=[],
|
||||
sys_prompt="",
|
||||
observe_window=None,
|
||||
console_silence=False,
|
||||
console_slience=False,
|
||||
):
|
||||
"""
|
||||
发送至chatGPT，等待回复，一次性完成，不显示中间过程。但内部用stream的方法避免中途网线被掐。
|
||||
@@ -158,13 +149,12 @@ def get_predict_function(
|
||||
observe_window = None：
|
||||
用于负责跨越线程传递已经输出的部分，大部分时候仅仅为了fancy的视觉效果，留空即可。observe_window[0]：观测窗。observe_window[1]：看门狗
|
||||
"""
|
||||
from .bridge_all import model_info
|
||||
watch_dog_patience = 5 # 看门狗的耐心，设置5秒不准咬人 (咬的也不是人)
|
||||
watch_dog_patience = 5 # 看门狗的耐心，设置5秒不准咬人(咬的也不是人
|
||||
if len(APIKEY) == 0:
|
||||
raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
|
||||
if inputs == "":
|
||||
inputs = "你好👋"
|
||||
headers, payload = generate_message(
|
||||
headers, playload = generate_message(
|
||||
input=inputs,
|
||||
model=llm_kwargs["llm_model"],
|
||||
key=APIKEY,
|
||||
@@ -173,18 +163,26 @@ def get_predict_function(
|
||||
system_prompt=sys_prompt,
|
||||
temperature=llm_kwargs["temperature"],
|
||||
)
|
||||
|
||||
reasoning = model_info[llm_kwargs['llm_model']].get('enable_reasoning', False)
|
||||
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
from .bridge_all import model_info
|
||||
|
||||
endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
|
||||
if not disable_proxy:
|
||||
response = requests.post(
|
||||
endpoint,
|
||||
headers=headers,
|
||||
proxies=None if disable_proxy else proxies,
|
||||
json=payload,
|
||||
proxies=proxies,
|
||||
json=playload,
|
||||
stream=True,
|
||||
timeout=TIMEOUT_SECONDS,
|
||||
)
|
||||
else:
|
||||
response = requests.post(
|
||||
endpoint,
|
||||
headers=headers,
|
||||
json=playload,
|
||||
stream=True,
|
||||
timeout=TIMEOUT_SECONDS,
|
||||
)
|
||||
@@ -197,12 +195,9 @@ def get_predict_function(
|
||||
if MAX_RETRY != 0:
|
||||
logger.error(f"请求超时，正在重试 ({retry}/{MAX_RETRY}) ……")
|
||||
|
||||
stream_response = response.iter_lines()
|
||||
result = ""
|
||||
finish_reason = ""
|
||||
if reasoning:
|
||||
reasoning_buffer = ""
|
||||
|
||||
stream_response = response.iter_lines()
|
||||
while True:
|
||||
try:
|
||||
chunk = next(stream_response)
|
||||
@@ -212,9 +207,9 @@ def get_predict_function(
|
||||
break
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
response_text, reasoning_content, finish_reason, decoded_chunk = decode_chunk(chunk)
|
||||
response_text, finish_reason = decode_chunk(chunk)
|
||||
# 返回的数据流第一次为空，继续等待
|
||||
if response_text == "" and (reasoning == False or reasoning_content == "") and finish_reason != "False":
|
||||
if response_text == "" and finish_reason != "False":
|
||||
continue
|
||||
if response_text == "API_ERROR" and (
|
||||
finish_reason != "False" or finish_reason != "stop"
|
||||
@@ -228,12 +223,10 @@ def get_predict_function(
|
||||
if chunk:
|
||||
try:
|
||||
if finish_reason == "stop":
|
||||
if not console_silence:
|
||||
if not console_slience:
|
||||
print(f"[response] {result}")
|
||||
break
|
||||
result += response_text
|
||||
if reasoning:
|
||||
reasoning_buffer += reasoning_content
|
||||
if observe_window is not None:
|
||||
# 观测窗，把已经获取的数据显示出去
|
||||
if len(observe_window) >= 1:
|
||||
@@ -248,9 +241,6 @@ def get_predict_function(
|
||||
error_msg = chunk_decoded
|
||||
logger.error(error_msg)
|
||||
raise RuntimeError("Json解析不合常规")
|
||||
if reasoning:
|
||||
paragraphs = ''.join([f'<p style="margin: 1.25em 0;">{line}</p>' for line in reasoning_buffer.split('\n')])
|
||||
return f'''<div class="reasoning_process" >{paragraphs}</div>\n\n''' + result
|
||||
return result
|
||||
|
||||
def predict(
|
||||
@@ -269,10 +259,9 @@ def get_predict_function(
|
||||
inputs 是本次问询的输入
|
||||
top_p, temperature是chatGPT的内部调优参数
|
||||
history 是之前的对话列表（注意无论是inputs还是history，内容太长了都会触发token数量溢出的错误）
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yield出去，可以直接修改对话界面内容
|
||||
chatbot 为WebUI中显示的对话列表，修改它，然后yeild出去，可以直接修改对话界面内容
|
||||
additional_fn代表点击的哪个按钮，按钮见functional.py
|
||||
"""
|
||||
from .bridge_all import model_info
|
||||
if len(APIKEY) == 0:
|
||||
raise RuntimeError(f"APIKEY为空,请检查配置文件的{APIKEY}")
|
||||
if inputs == "":
|
||||
@@ -300,7 +289,7 @@ def get_predict_function(
|
||||
) # 刷新界面
|
||||
time.sleep(2)
|
||||
|
||||
headers, payload = generate_message(
|
||||
headers, playload = generate_message(
|
||||
input=inputs,
|
||||
model=llm_kwargs["llm_model"],
|
||||
key=APIKEY,
|
||||
@@ -310,19 +299,28 @@ def get_predict_function(
|
||||
temperature=llm_kwargs["temperature"],
|
||||
)
|
||||
|
||||
reasoning = model_info[llm_kwargs['llm_model']].get('enable_reasoning', False)
|
||||
|
||||
history.append(inputs)
|
||||
history.append("")
|
||||
retry = 0
|
||||
while True:
|
||||
try:
|
||||
from .bridge_all import model_info
|
||||
|
||||
endpoint = model_info[llm_kwargs["llm_model"]]["endpoint"]
|
||||
if not disable_proxy:
|
||||
response = requests.post(
|
||||
endpoint,
|
||||
headers=headers,
|
||||
proxies=None if disable_proxy else proxies,
|
||||
json=payload,
|
||||
proxies=proxies,
|
||||
json=playload,
|
||||
stream=True,
|
||||
timeout=TIMEOUT_SECONDS,
|
||||
)
|
||||
else:
|
||||
response = requests.post(
|
||||
endpoint,
|
||||
headers=headers,
|
||||
json=playload,
|
||||
stream=True,
|
||||
timeout=TIMEOUT_SECONDS,
|
||||
)
|
||||
@@ -340,27 +338,18 @@ def get_predict_function(
|
||||
raise TimeoutError
|
||||
|
||||
gpt_replying_buffer = ""
|
||||
if reasoning:
|
||||
gpt_reasoning_buffer = ""
|
||||
|
||||
stream_response = response.iter_lines()
|
||||
wait_counter = 0
|
||||
while True:
|
||||
try:
|
||||
chunk = next(stream_response)
|
||||
except StopIteration:
|
||||
if wait_counter != 0 and gpt_replying_buffer == "":
|
||||
yield from update_ui_latest_msg(lastmsg="模型调用失败 ...", chatbot=chatbot, history=history, msg="failed")
|
||||
break
|
||||
except requests.exceptions.ConnectionError:
|
||||
chunk = next(stream_response) # 失败了，重试一次？再失败就没办法了。
|
||||
response_text, reasoning_content, finish_reason, decoded_chunk = decode_chunk(chunk)
|
||||
if decoded_chunk == ': keep-alive':
|
||||
wait_counter += 1
|
||||
yield from update_ui_latest_msg(lastmsg="等待中 " + "".join(["."] * (wait_counter%10)), chatbot=chatbot, history=history, msg="waiting ...")
|
||||
continue
|
||||
response_text, finish_reason = decode_chunk(chunk)
|
||||
# 返回的数据流第一次为空，继续等待
|
||||
if response_text == "" and (reasoning == False or reasoning_content == "") and finish_reason != "False":
|
||||
if response_text == "" and finish_reason != "False":
|
||||
status_text = f"finish_reason: {finish_reason}"
|
||||
yield from update_ui(
|
||||
chatbot=chatbot, history=history, msg=status_text
|
||||
@@ -375,7 +364,7 @@ def get_predict_function(
|
||||
chunk_decoded = chunk.decode()
|
||||
chatbot[-1] = (
|
||||
chatbot[-1][0],
|
||||
f"[Local Message] {finish_reason}, 获得以下报错信息：\n"
|
||||
"[Local Message] {finish_reason},获得以下报错信息：\n"
|
||||
+ chunk_decoded,
|
||||
)
|
||||
yield from update_ui(
|
||||
@@ -390,12 +379,6 @@ def get_predict_function(
|
||||
logger.info(f"[response] {gpt_replying_buffer}")
|
||||
break
|
||||
status_text = f"finish_reason: {finish_reason}"
|
||||
if reasoning:
|
||||
gpt_replying_buffer += response_text
|
||||
gpt_reasoning_buffer += reasoning_content
|
||||
paragraphs = ''.join([f'<p style="margin: 1.25em 0;">{line}</p>' for line in gpt_reasoning_buffer.split('\n')])
|
||||
history[-1] = f'<div class="reasoning_process">{paragraphs}</div>\n\n---\n\n' + gpt_replying_buffer
|
||||
else:
|
||||
gpt_replying_buffer += response_text
|
||||
# 如果这里抛出异常，一般是文本过长，详情见get_full_error的输出
|
||||
history[-1] = gpt_replying_buffer
|
||||
|
||||
@@ -1,7 +0,0 @@
|
||||
protobuf
|
||||
cpm_kernels
|
||||
torch>=1.10
|
||||
transformers>=4.44
|
||||
mdtex2html
|
||||
sentencepiece
|
||||
accelerate
|
||||
@@ -1,4 +1,4 @@
|
||||
https://public.agent-matrix.com/publish/gradio-3.32.12-py3-none-any.whl
|
||||
https://public.agent-matrix.com/publish/gradio-3.32.10-py3-none-any.whl
|
||||
fastapi==0.110
|
||||
gradio-client==0.8
|
||||
pypdf2==2.12.1
|
||||
@@ -13,7 +13,7 @@ scipdf_parser>=0.52
|
||||
spacy==3.7.4
|
||||
anthropic>=0.18.1
|
||||
python-markdown-math
|
||||
pymdown-extensions>=10.14
|
||||
pymdown-extensions
|
||||
websocket-client
|
||||
beautifulsoup4
|
||||
prompt_toolkit
|
||||
@@ -25,7 +25,7 @@ pyautogen
|
||||
colorama
|
||||
Markdown
|
||||
pygments
|
||||
edge-tts>=7.0.0
|
||||
edge-tts
|
||||
pymupdf
|
||||
openai
|
||||
rjsmin
|
||||
|
||||
@@ -2,7 +2,6 @@ import markdown
|
||||
import re
|
||||
import os
|
||||
import math
|
||||
import html
|
||||
|
||||
from loguru import logger
|
||||
from textwrap import dedent
|
||||
@@ -385,24 +384,6 @@ def markdown_convertion(txt):
|
||||
)
|
||||
|
||||
|
||||
def code_block_title_replace_format(match):
|
||||
lang = match.group(1)
|
||||
filename = match.group(2)
|
||||
return f"```{lang} {{title=\"{filename}\"}}\n"
|
||||
|
||||
|
||||
def get_last_backticks_indent(text):
|
||||
# 从后向前查找最后一个 ```
|
||||
lines = text.splitlines()
|
||||
for line in reversed(lines):
|
||||
if '```' in line:
|
||||
# 计算前面的空格数量
|
||||
indent = len(line) - len(line.lstrip())
|
||||
return indent
|
||||
return 0 # 如果没找到返回0
|
||||
|
||||
|
||||
@lru_cache(maxsize=16) # 使用lru缓存
|
||||
def close_up_code_segment_during_stream(gpt_reply):
|
||||
"""
|
||||
在gpt输出代码的中途（输出了前面的```，但还没输出完后面的```），补上后面的```
|
||||
@@ -416,12 +397,6 @@ def close_up_code_segment_during_stream(gpt_reply):
|
||||
"""
|
||||
if "```" not in gpt_reply:
|
||||
return gpt_reply
|
||||
|
||||
# replace [```python:warp.py] to [```python {title="warp.py"}]
|
||||
pattern = re.compile(r"```([a-z]{1,12}):([^:\n]{1,35}\.([a-zA-Z^:\n]{1,3}))\n")
|
||||
if pattern.search(gpt_reply):
|
||||
gpt_reply = pattern.sub(code_block_title_replace_format, gpt_reply)
|
||||
|
||||
if gpt_reply.endswith("```"):
|
||||
return gpt_reply
|
||||
|
||||
@@ -429,11 +404,7 @@ def close_up_code_segment_during_stream(gpt_reply):
|
||||
segments = gpt_reply.split("```")
|
||||
n_mark = len(segments) - 1
|
||||
if n_mark % 2 == 1:
|
||||
try:
|
||||
num_padding = get_last_backticks_indent(gpt_reply)
|
||||
except:
|
||||
num_padding = 0
|
||||
return gpt_reply + "\n" + " "*num_padding + "```" # 输出代码片段中！
|
||||
return gpt_reply + "\n```" # 输出代码片段中！
|
||||
else:
|
||||
return gpt_reply
|
||||
|
||||
@@ -450,19 +421,6 @@ def special_render_issues_for_mermaid(text):
|
||||
return text
|
||||
|
||||
|
||||
def contain_html_tag(text):
|
||||
"""
|
||||
判断文本中是否包含HTML标签。
|
||||
"""
|
||||
pattern = r'</?([a-zA-Z0-9_]{3,16})>|<script\s+[^>]*src=["\']([^"\']+)["\'][^>]*>'
|
||||
return re.search(pattern, text) is not None
|
||||
|
||||
|
||||
def contain_image(text):
|
||||
pattern = r'<br/><br/><div align="center"><img src="file=(.*?)" base64="(.*?)"></div>'
|
||||
return re.search(pattern, text) is not None
|
||||
|
||||
|
||||
def compat_non_markdown_input(text):
|
||||
"""
|
||||
改善非markdown输入的显示效果，例如将空格转换为 ，将换行符转换为</br>等。
|
||||
@@ -471,13 +429,9 @@ def compat_non_markdown_input(text):
|
||||
# careful input：markdown输入
|
||||
text = special_render_issues_for_mermaid(text) # 处理特殊的渲染问题
|
||||
return text
|
||||
elif ("<" in text) and (">" in text) and contain_html_tag(text):
|
||||
elif "</div>" in text:
|
||||
# careful input：html输入
|
||||
if contain_image(text):
|
||||
return text
|
||||
else:
|
||||
escaped_text = html.escape(text)
|
||||
return escaped_text
|
||||
else:
|
||||
# whatever input：非markdown输入
|
||||
lines = text.split("\n")
|
||||
|
||||
@@ -8,7 +8,7 @@ def is_full_width_char(ch):
|
||||
return True # CJK标点符号
|
||||
return False
|
||||
|
||||
def scrolling_visual_effect(text, scroller_max_len):
|
||||
def scolling_visual_effect(text, scroller_max_len):
|
||||
text = text.\
|
||||
replace('\n', '').replace('`', '.').replace(' ', '.').replace('<br/>', '.....').replace('$', '.')
|
||||
place_take_cnt = 0
|
||||
|
||||
@@ -85,7 +85,7 @@ def get_chat_default_kwargs():
|
||||
"history": [],
|
||||
"sys_prompt": "You are AI assistant",
|
||||
"observe_window": None,
|
||||
"console_silence": False,
|
||||
"console_slience": False,
|
||||
}
|
||||
|
||||
return default_chat_kwargs
|
||||
|
||||
@@ -77,28 +77,16 @@ def make_history_cache():
|
||||
# 定义 后端state（history）、前端（history_cache）、后端setter（history_cache_update）三兄弟
|
||||
import gradio as gr
|
||||
# 定义history的后端state
|
||||
# history = gr.State([])
|
||||
history = gr.Textbox(visible=False, elem_id="history-ng")
|
||||
# # 定义history的一个孪生的前端存储区（隐藏）
|
||||
# history_cache = gr.Textbox(visible=False, elem_id="history_cache")
|
||||
# # 定义history_cache->history的更新方法（隐藏）。在触发这个按钮时，会先执行js代码更新history_cache，然后再执行python代码更新history
|
||||
# def process_history_cache(history_cache):
|
||||
# return json.loads(history_cache)
|
||||
# # 另一种更简单的setter方法
|
||||
# history_cache_update = gr.Button("", elem_id="elem_update_history", visible=False).click(
|
||||
# process_history_cache, inputs=[history_cache], outputs=[history])
|
||||
# # save history to history_cache
|
||||
# def process_history_cache(history_cache):
|
||||
# return json.dumps(history_cache)
|
||||
# # 定义history->history_cache的更新方法（隐藏）
|
||||
# def sync_history_cache(history):
|
||||
# print("sync_history_cache", history)
|
||||
# return json.dumps(history)
|
||||
# # history.change(sync_history_cache, inputs=[history], outputs=[history_cache])
|
||||
|
||||
# # history_cache_sync = gr.Button("", elem_id="elem_sync_history", visible=False).click(
|
||||
# # lambda history: (json.dumps(history)), inputs=[history_cache], outputs=[history])
|
||||
return history, None, None
|
||||
history = gr.State([])
|
||||
# 定义history的一个孪生的前端存储区（隐藏）
|
||||
history_cache = gr.Textbox(visible=False, elem_id="history_cache")
|
||||
# 定义history_cache->history的更新方法（隐藏）。在触发这个按钮时，会先执行js代码更新history_cache，然后再执行python代码更新history
|
||||
def process_history_cache(history_cache):
|
||||
return json.loads(history_cache)
|
||||
# 另一种更简单的setter方法
|
||||
history_cache_update = gr.Button("", elem_id="elem_update_history", visible=False).click(
|
||||
process_history_cache, inputs=[history_cache], outputs=[history])
|
||||
return history, history_cache, history_cache_update
|
||||
|
||||
|
||||
|
||||
|
||||
@@ -1,83 +0,0 @@
|
||||
import requests
|
||||
import pickle
|
||||
import io
|
||||
import os
|
||||
from pydantic import BaseModel, Field
|
||||
from typing import Optional, Dict, Any
|
||||
from loguru import logger
|
||||
|
||||
class DockerServiceApiComModel(BaseModel):
|
||||
client_command: Optional[str] = Field(default=None, title="Client command", description="The command to be executed on the client side")
|
||||
client_file_attach: Optional[dict] = Field(default=None, title="Client file attach", description="The file to be attached to the client side")
|
||||
server_message: Optional[Any] = Field(default=None, title="Server standard error", description="The standard error from the server side")
|
||||
server_std_err: Optional[str] = Field(default=None, title="Server standard error", description="The standard error from the server side")
|
||||
server_std_out: Optional[str] = Field(default=None, title="Server standard output", description="The standard output from the server side")
|
||||
server_file_attach: Optional[dict] = Field(default=None, title="Server file attach", description="The file to be attached to the server side")
|
||||
|
||||
def process_received(received: DockerServiceApiComModel, save_file_dir="./daas_output", output_manifest=None):
|
||||
# Process the received data
|
||||
if received.server_message:
|
||||
try:
|
||||
output_manifest['server_message'] += received.server_message
|
||||
except:
|
||||
output_manifest['server_message'] = received.server_message
|
||||
if received.server_std_err:
|
||||
output_manifest['server_std_err'] += received.server_std_err
|
||||
if received.server_std_out:
|
||||
output_manifest['server_std_out'] += received.server_std_out
|
||||
if received.server_file_attach:
|
||||
# print(f"Recv file attach: {received.server_file_attach}")
|
||||
for file_name, file_content in received.server_file_attach.items():
|
||||
new_fp = os.path.join(save_file_dir, file_name)
|
||||
new_fp_dir = os.path.dirname(new_fp)
|
||||
if not os.path.exists(new_fp_dir):
|
||||
os.makedirs(new_fp_dir, exist_ok=True)
|
||||
with open(new_fp, 'wb') as f:
|
||||
f.write(file_content)
|
||||
output_manifest['server_file_attach'].append(new_fp)
|
||||
return output_manifest
|
||||
|
||||
def stream_daas(docker_service_api_com_model, server_url, save_file_dir):
|
||||
# Prepare the file
|
||||
# Pickle the object
|
||||
pickled_data = pickle.dumps(docker_service_api_com_model)
|
||||
|
||||
# Create a file-like object from the pickled data
|
||||
file_obj = io.BytesIO(pickled_data)
|
||||
|
||||
# Prepare the file for sending
|
||||
files = {'file': ('docker_service_api_com_model.pkl', file_obj, 'application/octet-stream')}
|
||||
|
||||
# Send the POST request
|
||||
response = requests.post(server_url, files=files, stream=True)
|
||||
|
||||
max_full_package_size = 1024 * 1024 * 1024 * 1 # 1 GB
|
||||
|
||||
received_output_manifest = {}
|
||||
received_output_manifest['server_message'] = ""
|
||||
received_output_manifest['server_std_err'] = ""
|
||||
received_output_manifest['server_std_out'] = ""
|
||||
received_output_manifest['server_file_attach'] = []
|
||||
|
||||
# Check if the request was successful
|
||||
if response.status_code == 200:
|
||||
# Process the streaming response
|
||||
chunk_buf = None
|
||||
for chunk in response.iter_content(max_full_package_size):
|
||||
if chunk:
|
||||
if chunk_buf is None: chunk_buf = chunk
|
||||
else: chunk_buf += chunk
|
||||
|
||||
try:
|
||||
received = pickle.loads(chunk_buf)
|
||||
chunk_buf = None
|
||||
received_output_manifest = process_received(received, save_file_dir, output_manifest = received_output_manifest)
|
||||
yield received_output_manifest
|
||||
except Exception as e:
|
||||
# logger.error(f"pickle data was truncated, but don't worry, we will continue to receive the rest of the data.")
|
||||
continue
|
||||
|
||||
else:
|
||||
logger.error(f"Error: Received status code {response.status_code}, response.text: {response.text}")
|
||||
|
||||
return received_output_manifest
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user